{ "name": "Austronesian", "depth": 0, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Atayalic", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Atayal", "depth": 2, "iso_1_code": null, "iso_3_code": "tay", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1438", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sediq", "depth": 2, "iso_1_code": null, "iso_3_code": "trv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1439", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1437", "native_tokenizers": [], "scripts": [] }, { "name": "Bunun", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bunun", "depth": 2, "iso_1_code": null, "iso_3_code": "bnn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1441", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1440", "native_tokenizers": [], "scripts": [] }, { "name": "East Formosan", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Amis", "depth": 3, "iso_1_code": null, "iso_3_code": "ami", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1444", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sakizaya", "depth": 3, "iso_1_code": null, "iso_3_code": "szy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1445", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1443", "native_tokenizers": [], "scripts": [] }, { "name": "Northern", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Basay", "depth": 3, "iso_1_code": null, "iso_3_code": "byq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1447", "native_tokenizers": [], "scripts": [] }, { "name": "Kavalan", "depth": 3, "iso_1_code": null, "iso_3_code": "ckv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1448", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1446", "native_tokenizers": [], "scripts": [] }, { "name": "Southwest", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Siraya", "depth": 3, "iso_1_code": null, "iso_3_code": "fos", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1450", "native_tokenizers": [], "scripts": [] }, { "name": "Taivoan", "depth": 3, "iso_1_code": null, "iso_3_code": "tvx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1451", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1449", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1442", "native_tokenizers": [], "scripts": [] }, { "name": "Malayo-Polynesian", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agta, Villa Viciosa", "depth": 2, "iso_1_code": null, "iso_3_code": "dyg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1453", "native_tokenizers": [], "scripts": [] }, { "name": "Bali-Sasak-Sumbawa", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bali", "depth": 3, "iso_1_code": null, "iso_3_code": "ban", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1455", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sasak-Sumbawa", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sasak", "depth": 4, "iso_1_code": null, "iso_3_code": "sas", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1457", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sumbawa", "depth": 4, "iso_1_code": null, "iso_3_code": "smw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1458", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1456", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1454", "native_tokenizers": [], "scripts": [] }, { "name": "Bashiic", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ivatan", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ibatan", "depth": 4, "iso_1_code": null, "iso_3_code": "ivb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1461", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ivatan", "depth": 4, "iso_1_code": null, "iso_3_code": "ivv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1462", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1460", "native_tokenizers": [], "scripts": [] }, { "name": "Yami", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yami", "depth": 4, "iso_1_code": null, "iso_3_code": "tao", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1464", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1463", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1459", "native_tokenizers": [], "scripts": [] }, { "name": "Bilic", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bagobo-Klata", "depth": 3, "iso_1_code": null, "iso_3_code": "bgi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1466", "native_tokenizers": [], "scripts": [] }, { "name": "Teduray", "depth": 3, "iso_1_code": null, "iso_3_code": "tiy", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1467", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Blaan", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Blaan, Koronadal", "depth": 4, "iso_1_code": null, "iso_3_code": "bpr", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1469", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Blaan, Sarangani", "depth": 4, "iso_1_code": null, "iso_3_code": "bps", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1470", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1468", "native_tokenizers": [], "scripts": [] }, { "name": "Tboli", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tboli", "depth": 4, "iso_1_code": null, "iso_3_code": "tbl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1472", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1471", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1465", "native_tokenizers": [], "scripts": [] }, { "name": "Celebic", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Saluan-Banggai", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Banggai", "depth": 6, "iso_1_code": null, "iso_3_code": "bgz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1477", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Balantak", "depth": 6, "iso_1_code": null, "iso_3_code": "blz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1478", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1476", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Andio", "depth": 6, "iso_1_code": null, "iso_3_code": "bzb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1480", "native_tokenizers": [], "scripts": [] }, { "name": "Saluanic", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bobongko", "depth": 7, "iso_1_code": null, "iso_3_code": "bgb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1482", "native_tokenizers": [], "scripts": [] }, { "name": "Saluan", "depth": 7, "iso_1_code": null, "iso_3_code": "loe", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1483", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Batui", "depth": 7, "iso_1_code": null, "iso_3_code": "zbt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1484", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1481", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1479", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1475", "native_tokenizers": [], "scripts": [] }, { "name": "Southeastern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bungku-Tolaki", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Coast", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bungku", "depth": 8, "iso_1_code": null, "iso_3_code": "bkz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1489", "native_tokenizers": [], "scripts": [] }, { "name": "Bahonsuai", "depth": 8, "iso_1_code": null, "iso_3_code": "bsu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1490", "native_tokenizers": [], "scripts": [] }, { "name": "Wawonii", "depth": 8, "iso_1_code": null, "iso_3_code": "wow", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1491", "native_tokenizers": [], "scripts": [] }, { "name": "Mori Bawah", "depth": 8, "iso_1_code": null, "iso_3_code": "xmz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1492", "native_tokenizers": [], "scripts": [] }, { "name": "Kulisusu", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Taloki", "depth": 9, "iso_1_code": null, "iso_3_code": "tlk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1494", "native_tokenizers": [], "scripts": [] }, { "name": "Kulisusu", "depth": 9, "iso_1_code": null, "iso_3_code": "vkl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1495", "native_tokenizers": [], "scripts": [] }, { "name": "Koroni", "depth": 9, "iso_1_code": null, "iso_3_code": "xkq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1496", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1493", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1488", "native_tokenizers": [], "scripts": [] }, { "name": "Southwest", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Moronene", "depth": 8, "iso_1_code": null, "iso_3_code": "mqn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1498", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1497", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1487", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Interior", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mori Atas", "depth": 8, "iso_1_code": null, "iso_3_code": "mzq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1501", "native_tokenizers": [], "scripts": [] }, { "name": "Padoe", "depth": 8, "iso_1_code": null, "iso_3_code": "pdo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1502", "native_tokenizers": [], "scripts": [] }, { "name": "Tomadino", "depth": 8, "iso_1_code": null, "iso_3_code": "tdi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1503", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1500", "native_tokenizers": [], "scripts": [] }, { "name": "West Coast", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tolaki", "depth": 8, "iso_1_code": null, "iso_3_code": "lbw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1505", "native_tokenizers": [], "scripts": [] }, { "name": "Rahambuu", "depth": 8, "iso_1_code": null, "iso_3_code": "raz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1506", "native_tokenizers": [], "scripts": [] }, { "name": "Kodeoha", "depth": 8, "iso_1_code": null, "iso_3_code": "vko", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1507", "native_tokenizers": [], "scripts": [] }, { "name": "Waru", "depth": 8, "iso_1_code": null, "iso_3_code": "wru", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1508", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1504", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1499", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1486", "native_tokenizers": [], "scripts": [] }, { "name": "Muna-Buton", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nuclear Muna-Buton", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buton", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Buton", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lasalimu", "depth": 9, "iso_1_code": null, "iso_3_code": "llm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1513", "native_tokenizers": [], "scripts": [] }, { "name": "Kumbewaha", "depth": 9, "iso_1_code": null, "iso_3_code": "xks", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1514", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1512", "native_tokenizers": [], "scripts": [] }, { "name": "West Buton", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cia-Cia", "depth": 9, "iso_1_code": null, "iso_3_code": "cia", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1516", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1515", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1511", "native_tokenizers": [], "scripts": [] }, { "name": "Munan", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Busoa", "depth": 8, "iso_1_code": null, "iso_3_code": "bup", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1518", "native_tokenizers": [], "scripts": [] }, { "name": "Munic", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kaimbulawa", "depth": 9, "iso_1_code": null, "iso_3_code": "zka", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1520", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Liabuku", "depth": 10, "iso_1_code": null, "iso_3_code": "lix", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1522", "native_tokenizers": [], "scripts": [] }, { "name": "Muna", "depth": 10, "iso_1_code": null, "iso_3_code": "mnb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1523", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Pancana", "depth": 10, "iso_1_code": null, "iso_3_code": "pnp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1524", "native_tokenizers": [], "scripts": [] }, { "name": "Kioko", "depth": 10, "iso_1_code": null, "iso_3_code": "ues", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1525", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1521", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1519", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1517", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1510", "native_tokenizers": [], "scripts": [] }, { "name": "Tukangbesi-Bonerate", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tukang Besi South", "depth": 7, "iso_1_code": null, "iso_3_code": "bhq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1527", "native_tokenizers": [], "scripts": [] }, { "name": "Bonerate", "depth": 7, "iso_1_code": null, "iso_3_code": "bna", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1528", "native_tokenizers": [], "scripts": [] }, { "name": "Tukang Besi North", "depth": 7, "iso_1_code": null, "iso_3_code": "khc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1529", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1526", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1509", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1485", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1474", "native_tokenizers": [], "scripts": [] }, { "name": "Kaili-Pamona", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kaili", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Baras", "depth": 6, "iso_1_code": null, "iso_3_code": "brs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1533", "native_tokenizers": [], "scripts": [] }, { "name": "Tado", "depth": 6, "iso_1_code": null, "iso_3_code": "klw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1534", "native_tokenizers": [], "scripts": [] }, { "name": "Kaili, Da\u2019a", "depth": 6, "iso_1_code": null, "iso_3_code": "kzf", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1535", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kaili, Ledo", "depth": 6, "iso_1_code": null, "iso_3_code": "lew", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1536", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Moma", "depth": 6, "iso_1_code": null, "iso_3_code": "myl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1537", "native_tokenizers": [], "scripts": [] }, { "name": "Topoiyo", "depth": 6, "iso_1_code": null, "iso_3_code": "toy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1538", "native_tokenizers": [], "scripts": [] }, { "name": "Sedoa", "depth": 6, "iso_1_code": null, "iso_3_code": "tvw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1539", "native_tokenizers": [], "scripts": [] }, { "name": "Kaili, Unde", "depth": 6, "iso_1_code": null, "iso_3_code": "unz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1540", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1532", "native_tokenizers": [], "scripts": [] }, { "name": "Pamona", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pamona", "depth": 6, "iso_1_code": null, "iso_3_code": "pmf", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1542", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tombelala", "depth": 6, "iso_1_code": null, "iso_3_code": "ttp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1543", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1541", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1531", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rampi", "depth": 5, "iso_1_code": null, "iso_3_code": "lje", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1545", "native_tokenizers": [], "scripts": [] }, { "name": "Uma", "depth": 5, "iso_1_code": null, "iso_3_code": "ppk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1546", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sarudu", "depth": 5, "iso_1_code": null, "iso_3_code": "sdu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1547", "native_tokenizers": [], "scripts": [] }, { "name": "Badaic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Behoa", "depth": 6, "iso_1_code": null, "iso_3_code": "bep", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1549", "native_tokenizers": [], "scripts": [] }, { "name": "Bada", "depth": 6, "iso_1_code": null, "iso_3_code": "bhz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1550", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Napu", "depth": 6, "iso_1_code": null, "iso_3_code": "npy", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1551", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1548", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1544", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1530", "native_tokenizers": [], "scripts": [] }, { "name": "Tomini-Tolitoli", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tolitoli", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Boano", "depth": 5, "iso_1_code": null, "iso_3_code": "bzl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1554", "native_tokenizers": [], "scripts": [] }, { "name": "Totoli", "depth": 5, "iso_1_code": null, "iso_3_code": "txe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1555", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1553", "native_tokenizers": [], "scripts": [] }, { "name": "Tomini", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dondo", "depth": 6, "iso_1_code": null, "iso_3_code": "dok", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1558", "native_tokenizers": [], "scripts": [] }, { "name": "Lauje", "depth": 6, "iso_1_code": null, "iso_3_code": "law", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1559", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tomini", "depth": 6, "iso_1_code": null, "iso_3_code": "txm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1560", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1557", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Balaesang", "depth": 6, "iso_1_code": null, "iso_3_code": "bls", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1562", "native_tokenizers": [], "scripts": [] }, { "name": "Dampelas", "depth": 6, "iso_1_code": null, "iso_3_code": "dms", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1563", "native_tokenizers": [], "scripts": [] }, { "name": "Taje", "depth": 6, "iso_1_code": null, "iso_3_code": "pee", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1564", "native_tokenizers": [], "scripts": [] }, { "name": "Tajio", "depth": 6, "iso_1_code": null, "iso_3_code": "tdj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1565", "native_tokenizers": [], "scripts": [] }, { "name": "Pendau", "depth": 6, "iso_1_code": null, "iso_3_code": "ums", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1566", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1561", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1556", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1552", "native_tokenizers": [], "scripts": [] }, { "name": "Wotu-Wolio", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Wotu", "depth": 4, "iso_1_code": null, "iso_3_code": "wtw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1568", "native_tokenizers": [], "scripts": [] }, { "name": "Kalao", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kalao", "depth": 5, "iso_1_code": null, "iso_3_code": "kly", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1570", "native_tokenizers": [], "scripts": [] }, { "name": "Laiyolo", "depth": 5, "iso_1_code": null, "iso_3_code": "lji", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1571", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1569", "native_tokenizers": [], "scripts": [] }, { "name": "Wolio-Kamaru", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kamaru", "depth": 5, "iso_1_code": null, "iso_3_code": "kgx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1573", "native_tokenizers": [], "scripts": [] }, { "name": "Wolio", "depth": 5, "iso_1_code": null, "iso_3_code": "wlo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1574", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1572", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1567", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1473", "native_tokenizers": [], "scripts": [] }, { "name": "Central Luzon", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pampangan", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kapampangan", "depth": 4, "iso_1_code": null, "iso_3_code": "pam", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1577", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1576", "native_tokenizers": [], "scripts": [] }, { "name": "Sambalic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ayta, Ambala", "depth": 4, "iso_1_code": null, "iso_3_code": "abc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1579", "native_tokenizers": [], "scripts": [] }, { "name": "Ayta, Abellen", "depth": 4, "iso_1_code": null, "iso_3_code": "abp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1580", "native_tokenizers": [], "scripts": [] }, { "name": "Ayta, Magbukun", "depth": 4, "iso_1_code": null, "iso_3_code": "ayt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1581", "native_tokenizers": [], "scripts": [] }, { "name": "Ayta, Mag-Indi", "depth": 4, "iso_1_code": null, "iso_3_code": "blx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1582", "native_tokenizers": [], "scripts": [] }, { "name": "Sambal, Botolan", "depth": 4, "iso_1_code": null, "iso_3_code": "sbl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1583", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ayta, Mag-antsi", "depth": 4, "iso_1_code": null, "iso_3_code": "sgb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1584", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bolinao", "depth": 4, "iso_1_code": null, "iso_3_code": "smk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1585", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sambal", "depth": 4, "iso_1_code": null, "iso_3_code": "xsb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1586", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1578", "native_tokenizers": [], "scripts": [] }, { "name": "Sinauna", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dumagat, Remontado", "depth": 4, "iso_1_code": null, "iso_3_code": "agv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1588", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1587", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1575", "native_tokenizers": [], "scripts": [] }, { "name": "Central-Eastern Malayo-Polynesian", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aru", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Barakai", "depth": 4, "iso_1_code": null, "iso_3_code": "baj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1591", "native_tokenizers": [], "scripts": [] }, { "name": "Gwatlelir", "depth": 4, "iso_1_code": null, "iso_3_code": "bay", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1592", "native_tokenizers": [], "scripts": [] }, { "name": "Koba", "depth": 4, "iso_1_code": null, "iso_3_code": "kpd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1593", "native_tokenizers": [], "scripts": [] }, { "name": "Dobel", "depth": 4, "iso_1_code": null, "iso_3_code": "kvo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1594", "native_tokenizers": [], "scripts": [] }, { "name": "Kompane", "depth": 4, "iso_1_code": null, "iso_3_code": "kvp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1595", "native_tokenizers": [], "scripts": [] }, { "name": "Kola", "depth": 4, "iso_1_code": null, "iso_3_code": "kvv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1596", "native_tokenizers": [], "scripts": [] }, { "name": "Karey", "depth": 4, "iso_1_code": null, "iso_3_code": "kyd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1597", "native_tokenizers": [], "scripts": [] }, { "name": "Lola", "depth": 4, "iso_1_code": null, "iso_3_code": "lcd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1598", "native_tokenizers": [], "scripts": [] }, { "name": "Lorang", "depth": 4, "iso_1_code": null, "iso_3_code": "lrn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1599", "native_tokenizers": [], "scripts": [] }, { "name": "Mariri", "depth": 4, "iso_1_code": null, "iso_3_code": "mqi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1600", "native_tokenizers": [], "scripts": [] }, { "name": "Tarangan, East", "depth": 4, "iso_1_code": null, "iso_3_code": "tre", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1601", "native_tokenizers": [], "scripts": [] }, { "name": "Tarangan, West", "depth": 4, "iso_1_code": null, "iso_3_code": "txn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1602", "native_tokenizers": [], "scripts": [] }, { "name": "Ujir", "depth": 4, "iso_1_code": null, "iso_3_code": "udj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1603", "native_tokenizers": [], "scripts": [] }, { "name": "Manombai", "depth": 4, "iso_1_code": null, "iso_3_code": "woo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1604", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1590", "native_tokenizers": [], "scripts": [] }, { "name": "Babar", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Babar, North", "depth": 5, "iso_1_code": null, "iso_3_code": "bcd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1607", "native_tokenizers": [], "scripts": [] }, { "name": "Dawera-Daweloor", "depth": 5, "iso_1_code": null, "iso_3_code": "ddw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1608", "native_tokenizers": [], "scripts": [] }, { "name": "Dai", "depth": 5, "iso_1_code": null, "iso_3_code": "dij", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1609", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1606", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Masela-South Babar", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Masela, West", "depth": 6, "iso_1_code": null, "iso_3_code": "mss", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1612", "native_tokenizers": [], "scripts": [] }, { "name": "Masela, Central", "depth": 6, "iso_1_code": null, "iso_3_code": "mxz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1613", "native_tokenizers": [], "scripts": [] }, { "name": "Serili", "depth": 6, "iso_1_code": null, "iso_3_code": "sve", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1614", "native_tokenizers": [], "scripts": [] }, { "name": "Babar, Southeast", "depth": 6, "iso_1_code": null, "iso_3_code": "vbb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1615", "native_tokenizers": [], "scripts": [] }, { "name": "Masela, East", "depth": 6, "iso_1_code": null, "iso_3_code": "vme", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1616", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1611", "native_tokenizers": [], "scripts": [] }, { "name": "Southwest Babar", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Emplawas", "depth": 6, "iso_1_code": null, "iso_3_code": "emw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1618", "native_tokenizers": [], "scripts": [] }, { "name": "Imroing", "depth": 6, "iso_1_code": null, "iso_3_code": "imr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1619", "native_tokenizers": [], "scripts": [] }, { "name": "Tela-Masbuar", "depth": 6, "iso_1_code": null, "iso_3_code": "tvm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1620", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1617", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1610", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1605", "native_tokenizers": [], "scripts": [] }, { "name": "Bima-Lembata", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Adonara", "depth": 4, "iso_1_code": null, "iso_3_code": "adr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1622", "native_tokenizers": [], "scripts": [] }, { "name": "Alor", "depth": 4, "iso_1_code": null, "iso_3_code": "aol", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1623", "native_tokenizers": [], "scripts": [] }, { "name": "Bima", "depth": 4, "iso_1_code": null, "iso_3_code": "bhp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1624", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ende", "depth": 4, "iso_1_code": null, "iso_3_code": "end", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1625", "native_tokenizers": [], "scripts": [] }, { "name": "Ile Ape", "depth": 4, "iso_1_code": null, "iso_3_code": "ila", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1626", "native_tokenizers": [], "scripts": [] }, { "name": "Kedang", "depth": 4, "iso_1_code": null, "iso_3_code": "ksx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1627", "native_tokenizers": [], "scripts": [] }, { "name": "Kepo\u2019", "depth": 4, "iso_1_code": null, "iso_3_code": "kuk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1628", "native_tokenizers": [], "scripts": [] }, { "name": "Komodo", "depth": 4, "iso_1_code": null, "iso_3_code": "kvh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1629", "native_tokenizers": [], "scripts": [] }, { "name": "Li\u2019o", "depth": 4, "iso_1_code": null, "iso_3_code": "ljl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1630", "native_tokenizers": [], "scripts": [] }, { "name": "Painara", "depth": 4, "iso_1_code": null, "iso_3_code": "lmf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1631", "native_tokenizers": [], "scripts": [] }, { "name": "Labalekan-Mingar", "depth": 4, "iso_1_code": null, "iso_3_code": "lmj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1632", "native_tokenizers": [], "scripts": [] }, { "name": "Lamatuka", "depth": 4, "iso_1_code": null, "iso_3_code": "lmq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1633", "native_tokenizers": [], "scripts": [] }, { "name": "Lamalera", "depth": 4, "iso_1_code": null, "iso_3_code": "lmr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1634", "native_tokenizers": [], "scripts": [] }, { "name": "Levuka", "depth": 4, "iso_1_code": null, "iso_3_code": "lvu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1635", "native_tokenizers": [], "scripts": [] }, { "name": "Lewoeleng", "depth": 4, "iso_1_code": null, "iso_3_code": "lwe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1636", "native_tokenizers": [], "scripts": [] }, { "name": "Lewotobi", "depth": 4, "iso_1_code": null, "iso_3_code": "lwt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1637", "native_tokenizers": [], "scripts": [] }, { "name": "Manggarai", "depth": 4, "iso_1_code": null, "iso_3_code": "mqy", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1638", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ngad\u2019a, Eastern", "depth": 4, "iso_1_code": null, "iso_3_code": "nea", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1639", "native_tokenizers": [], "scripts": [] }, { "name": "Nage", "depth": 4, "iso_1_code": null, "iso_3_code": "nxe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1640", "native_tokenizers": [], "scripts": [] }, { "name": "Ngad\u2019a", "depth": 4, "iso_1_code": null, "iso_3_code": "nxg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1641", "native_tokenizers": [], "scripts": [] }, { "name": "Palu\u2019e", "depth": 4, "iso_1_code": null, "iso_3_code": "ple", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1642", "native_tokenizers": [], "scripts": [] }, { "name": "Rembong", "depth": 4, "iso_1_code": null, "iso_3_code": "reb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1643", "native_tokenizers": [], "scripts": [] }, { "name": "Riung", "depth": 4, "iso_1_code": null, "iso_3_code": "riu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1644", "native_tokenizers": [], "scripts": [] }, { "name": "Rajong", "depth": 4, "iso_1_code": null, "iso_3_code": "rjg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1645", "native_tokenizers": [], "scripts": [] }, { "name": "Rongga", "depth": 4, "iso_1_code": null, "iso_3_code": "ror", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1646", "native_tokenizers": [], "scripts": [] }, { "name": "Sika", "depth": 4, "iso_1_code": null, "iso_3_code": "ski", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1647", "native_tokenizers": [], "scripts": [] }, { "name": "Lamaholot", "depth": 4, "iso_1_code": null, "iso_3_code": "slp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1648", "native_tokenizers": [], "scripts": [] }, { "name": "So\u2019a", "depth": 4, "iso_1_code": null, "iso_3_code": "ssq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1649", "native_tokenizers": [], "scripts": [] }, { "name": "Wae Rana", "depth": 4, "iso_1_code": null, "iso_3_code": "wrx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1650", "native_tokenizers": [], "scripts": [] }, { "name": "Ke\u2019o", "depth": 4, "iso_1_code": null, "iso_3_code": "xxk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1651", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1621", "native_tokenizers": [], "scripts": [] }, { "name": "Central Maluku", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ambelau", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ambelau", "depth": 5, "iso_1_code": null, "iso_3_code": "amv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1654", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1653", "native_tokenizers": [], "scripts": [] }, { "name": "Buru", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lisela", "depth": 5, "iso_1_code": null, "iso_3_code": "lcl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1656", "native_tokenizers": [], "scripts": [] }, { "name": "Buru", "depth": 5, "iso_1_code": null, "iso_3_code": "mhs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1657", "native_tokenizers": [], "scripts": [] }, { "name": "Moksela", "depth": 5, "iso_1_code": null, "iso_3_code": "vms", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1658", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1655", "native_tokenizers": [], "scripts": [] }, { "name": "East", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manipa", "depth": 5, "iso_1_code": null, "iso_3_code": "mqp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1660", "native_tokenizers": [], "scripts": [] }, { "name": "Banda-Geser", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Banda", "depth": 6, "iso_1_code": null, "iso_3_code": "bnd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1662", "native_tokenizers": [], "scripts": [] }, { "name": "Geser-Gorom", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bati", "depth": 7, "iso_1_code": null, "iso_3_code": "bvt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1664", "native_tokenizers": [], "scripts": [] }, { "name": "Geser-Gorom", "depth": 7, "iso_1_code": null, "iso_3_code": "ges", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1665", "native_tokenizers": [], "scripts": [] }, { "name": "Watubela", "depth": 7, "iso_1_code": null, "iso_3_code": "wah", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1666", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1663", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1661", "native_tokenizers": [], "scripts": [] }, { "name": "Seram", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bobot", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bobot", "depth": 7, "iso_1_code": null, "iso_3_code": "bty", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1669", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1668", "native_tokenizers": [], "scripts": [] }, { "name": "East Seram", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hoti", "depth": 7, "iso_1_code": null, "iso_3_code": "hti", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1671", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1670", "native_tokenizers": [], "scripts": [] }, { "name": "Manusela-Seti", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Benggoi", "depth": 7, "iso_1_code": null, "iso_3_code": "bgy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1673", "native_tokenizers": [], "scripts": [] }, { "name": "Huaulu", "depth": 7, "iso_1_code": null, "iso_3_code": "hud", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1674", "native_tokenizers": [], "scripts": [] }, { "name": "Salas", "depth": 7, "iso_1_code": null, "iso_3_code": "sgu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1675", "native_tokenizers": [], "scripts": [] }, { "name": "Liana-Seti", "depth": 7, "iso_1_code": null, "iso_3_code": "ste", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1676", "native_tokenizers": [], "scripts": [] }, { "name": "Sou Upaa", "depth": 7, "iso_1_code": null, "iso_3_code": "wha", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1677", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1672", "native_tokenizers": [], "scripts": [] }, { "name": "Masiwang", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Masiwang", "depth": 7, "iso_1_code": null, "iso_3_code": "bnf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1679", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1678", "native_tokenizers": [], "scripts": [] }, { "name": "Nunusaku", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayeli", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayeli", "depth": 8, "iso_1_code": null, "iso_3_code": "kzl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1682", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1681", "native_tokenizers": [], "scripts": [] }, { "name": "Piru Bay", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Haruku", "depth": 8, "iso_1_code": null, "iso_3_code": "hrk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1684", "native_tokenizers": [], "scripts": [] }, { "name": "East", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kaibobo", "depth": 9, "iso_1_code": null, "iso_3_code": "kzb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1686", "native_tokenizers": [], "scripts": [] }, { "name": "Sepa", "depth": 9, "iso_1_code": null, "iso_3_code": "spb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1687", "native_tokenizers": [], "scripts": [] }, { "name": "Sou Nama", "depth": 9, "iso_1_code": null, "iso_3_code": "tlt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1688", "native_tokenizers": [], "scripts": [] }, { "name": "Seram Straits", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ambon", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hitu", "depth": 11, "iso_1_code": null, "iso_3_code": "htu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1691", "native_tokenizers": [], "scripts": [] }, { "name": "Laha", "depth": 11, "iso_1_code": null, "iso_3_code": "lhh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1692", "native_tokenizers": [], "scripts": [] }, { "name": "Tulehu", "depth": 11, "iso_1_code": null, "iso_3_code": "tlu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1693", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1690", "native_tokenizers": [], "scripts": [] }, { "name": "Solehua", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Paulohi", "depth": 11, "iso_1_code": null, "iso_3_code": "plh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1695", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1694", "native_tokenizers": [], "scripts": [] }, { "name": "Uliase", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hatuhaha", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Elpaputi", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Amahai", "depth": 13, "iso_1_code": null, "iso_3_code": "amq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1699", "native_tokenizers": [], "scripts": [] }, { "name": "Nusa Laut", "depth": 13, "iso_1_code": null, "iso_3_code": "nul", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1700", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1698", "native_tokenizers": [], "scripts": [] }, { "name": "Saparua", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Latu", "depth": 13, "iso_1_code": null, "iso_3_code": "ltu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1702", "native_tokenizers": [], "scripts": [] }, { "name": "Saparua", "depth": 13, "iso_1_code": null, "iso_3_code": "spr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1703", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1701", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1697", "native_tokenizers": [], "scripts": [] }, { "name": "Kamarian", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kamarian", "depth": 12, "iso_1_code": null, "iso_3_code": "kzx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1705", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1704", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1696", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1689", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1685", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Asilulu", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Asilulu", "depth": 10, "iso_1_code": null, "iso_3_code": "asl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1708", "native_tokenizers": [], "scripts": [] }, { "name": "Seit-Kaitetu", "depth": 10, "iso_1_code": null, "iso_3_code": "hik", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1709", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1707", "native_tokenizers": [], "scripts": [] }, { "name": "Hoamoal", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Larike-Wakasihu", "depth": 10, "iso_1_code": null, "iso_3_code": "alo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1711", "native_tokenizers": [], "scripts": [] }, { "name": "Boano", "depth": 10, "iso_1_code": null, "iso_3_code": "bzn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1712", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1710", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1706", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1683", "native_tokenizers": [], "scripts": [] }, { "name": "Three Rivers", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yalahatan", "depth": 8, "iso_1_code": null, "iso_3_code": "jal", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1714", "native_tokenizers": [], "scripts": [] }, { "name": "Amalumute", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northwest Seram", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Luhu", "depth": 10, "iso_1_code": null, "iso_3_code": "lcq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1717", "native_tokenizers": [], "scripts": [] }, { "name": "Lisabata-Nuniali", "depth": 10, "iso_1_code": null, "iso_3_code": "lcs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1718", "native_tokenizers": [], "scripts": [] }, { "name": "Hulung", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hulung", "depth": 11, "iso_1_code": null, "iso_3_code": "huk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1720", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1719", "native_tokenizers": [], "scripts": [] }, { "name": "Loun", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Loun", "depth": 11, "iso_1_code": null, "iso_3_code": "lox", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1722", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1721", "native_tokenizers": [], "scripts": [] }, { "name": "Ulat Inai", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Alune", "depth": 11, "iso_1_code": null, "iso_3_code": "alp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1724", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Naka\u2019ela", "depth": 11, "iso_1_code": null, "iso_3_code": "nae", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1725", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1723", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1716", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1715", "native_tokenizers": [], "scripts": [] }, { "name": "Wemale", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Wemale", "depth": 9, "iso_1_code": null, "iso_3_code": "weo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1727", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1726", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1713", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1680", "native_tokenizers": [], "scripts": [] }, { "name": "Sawai-Nuaulu", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nuaulu, North", "depth": 7, "iso_1_code": null, "iso_3_code": "nni", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1729", "native_tokenizers": [], "scripts": [] }, { "name": "Nuaulu, South", "depth": 7, "iso_1_code": null, "iso_3_code": "nxl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1730", "native_tokenizers": [], "scripts": [] }, { "name": "Saleman", "depth": 7, "iso_1_code": null, "iso_3_code": "sau", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1731", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1728", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1667", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1659", "native_tokenizers": [], "scripts": [] }, { "name": "Sula", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mangole", "depth": 5, "iso_1_code": null, "iso_3_code": "mqc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1733", "native_tokenizers": [], "scripts": [] }, { "name": "Sula", "depth": 5, "iso_1_code": null, "iso_3_code": "szn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1734", "native_tokenizers": [], "scripts": [] }, { "name": "Taliabo", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kadai", "depth": 6, "iso_1_code": null, "iso_3_code": "kzd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1736", "native_tokenizers": [], "scripts": [] }, { "name": "Taliabu", "depth": 6, "iso_1_code": null, "iso_3_code": "tlv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1737", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1735", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1732", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1652", "native_tokenizers": [], "scripts": [] }, { "name": "Eastern Malayo-Polynesian", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Oceanic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Admiralty Islands", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manus", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Andra-Hus", "depth": 9, "iso_1_code": null, "iso_3_code": "anx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1744", "native_tokenizers": [], "scripts": [] }, { "name": "Elu", "depth": 9, "iso_1_code": null, "iso_3_code": "elu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1745", "native_tokenizers": [], "scripts": [] }, { "name": "Kurti", "depth": 9, "iso_1_code": null, "iso_3_code": "ktm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1746", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Koro", "depth": 9, "iso_1_code": null, "iso_3_code": "kxr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1747", "native_tokenizers": [], "scripts": [] }, { "name": "Leipon", "depth": 9, "iso_1_code": null, "iso_3_code": "lek", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1748", "native_tokenizers": [], "scripts": [] }, { "name": "Lele", "depth": 9, "iso_1_code": null, "iso_3_code": "lle", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1749", "native_tokenizers": [], "scripts": [] }, { "name": "Ponam", "depth": 9, "iso_1_code": null, "iso_3_code": "ncc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1750", "native_tokenizers": [], "scripts": [] }, { "name": "Nali", "depth": 9, "iso_1_code": null, "iso_3_code": "nss", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1751", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kele", "depth": 9, "iso_1_code": null, "iso_3_code": "sbc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1752", "native_tokenizers": [], "scripts": [] }, { "name": "Titan", "depth": 9, "iso_1_code": null, "iso_3_code": "ttv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1753", "native_tokenizers": [], "scripts": [] }, { "name": "Ere", "depth": 9, "iso_1_code": null, "iso_3_code": "twp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1754", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1743", "native_tokenizers": [], "scripts": [] }, { "name": "Mokoreng-Loniu", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Loniu", "depth": 9, "iso_1_code": null, "iso_3_code": "los", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1756", "native_tokenizers": [], "scripts": [] }, { "name": "Idio", "depth": 9, "iso_1_code": null, "iso_3_code": "mft", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1757", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1755", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bipi", "depth": 9, "iso_1_code": null, "iso_3_code": "biq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1759", "native_tokenizers": [], "scripts": [] }, { "name": "Likum", "depth": 9, "iso_1_code": null, "iso_3_code": "lib", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1760", "native_tokenizers": [], "scripts": [] }, { "name": "Nyindrou", "depth": 9, "iso_1_code": null, "iso_3_code": "lid", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1761", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Hermit", "depth": 9, "iso_1_code": null, "iso_3_code": "llf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1762", "native_tokenizers": [], "scripts": [] }, { "name": "Mondropolon", "depth": 9, "iso_1_code": null, "iso_3_code": "npn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1763", "native_tokenizers": [], "scripts": [] }, { "name": "Tulu-Bohuai", "depth": 9, "iso_1_code": null, "iso_3_code": "rak", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1764", "native_tokenizers": [], "scripts": [] }, { "name": "Sori-Harengan", "depth": 9, "iso_1_code": null, "iso_3_code": "sbh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1765", "native_tokenizers": [], "scripts": [] }, { "name": "Khehek", "depth": 9, "iso_1_code": null, "iso_3_code": "tlx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1766", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1758", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1742", "native_tokenizers": [], "scripts": [] }, { "name": "Pak-Tong", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pak-Tong", "depth": 8, "iso_1_code": null, "iso_3_code": "pkg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1768", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1767", "native_tokenizers": [], "scripts": [] }, { "name": "Southeast Islands", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Paluai", "depth": 8, "iso_1_code": null, "iso_3_code": "blq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1770", "native_tokenizers": [], "scripts": [] }, { "name": "Lenkau", "depth": 8, "iso_1_code": null, "iso_3_code": "ler", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1771", "native_tokenizers": [], "scripts": [] }, { "name": "Lou", "depth": 8, "iso_1_code": null, "iso_3_code": "loj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1772", "native_tokenizers": [], "scripts": [] }, { "name": "Neherneh", "depth": 8, "iso_1_code": null, "iso_3_code": "ncn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1773", "native_tokenizers": [], "scripts": [] }, { "name": "Penchal", "depth": 8, "iso_1_code": null, "iso_3_code": "pek", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1774", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1769", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1741", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kaniet", "depth": 7, "iso_1_code": null, "iso_3_code": "ktk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1776", "native_tokenizers": [], "scripts": [] }, { "name": "Seimat", "depth": 7, "iso_1_code": null, "iso_3_code": "ssg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1777", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Wuvulu-Aua", "depth": 7, "iso_1_code": null, "iso_3_code": "wuv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1778", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1775", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1740", "native_tokenizers": [], "scripts": [] }, { "name": "Central-Eastern Oceanic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Remote Oceanic", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Pacific", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Fijian-Polynesian", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Fijian", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Fijian", "depth": 10, "iso_1_code": "fj", "iso_3_code": "fij", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1784", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Gone Dau", "depth": 10, "iso_1_code": null, "iso_3_code": "goo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1785", "native_tokenizers": [], "scripts": [] }, { "name": "Lauan", "depth": 10, "iso_1_code": null, "iso_3_code": "llx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1786", "native_tokenizers": [], "scripts": [] }, { "name": "Lomaiviti", "depth": 10, "iso_1_code": null, "iso_3_code": "lmv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1787", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1783", "native_tokenizers": [], "scripts": [] }, { "name": "Polynesian", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nuclear", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rapa", "depth": 13, "iso_1_code": null, "iso_3_code": "ray", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1792", "native_tokenizers": [], "scripts": [] }, { "name": "Marquesic", "depth": 13, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hawaiian", "depth": 14, "iso_1_code": null, "iso_3_code": "haw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1794", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Marquesan, South", "depth": 14, "iso_1_code": null, "iso_3_code": "mqm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1795", "native_tokenizers": [], "scripts": [] }, { "name": "Marquesan, North", "depth": 14, "iso_1_code": null, "iso_3_code": "mrq", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1796", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Mangareva", "depth": 14, "iso_1_code": null, "iso_3_code": "mrv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1797", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1793", "native_tokenizers": [], "scripts": [] }, { "name": "Tahitic", "depth": 13, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Austral", "depth": 14, "iso_1_code": null, "iso_3_code": "aut", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1799", "native_tokenizers": [], "scripts": [] }, { "name": "Maori", "depth": 14, "iso_1_code": "mi", "iso_3_code": "mri", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1800", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tuamotuan", "depth": 14, "iso_1_code": null, "iso_3_code": "pmt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1801", "native_tokenizers": [], "scripts": [] }, { "name": "Penrhyn", "depth": 14, "iso_1_code": null, "iso_3_code": "pnh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1802", "native_tokenizers": [], "scripts": [] }, { "name": "Cook Islands Maori", "depth": 14, "iso_1_code": null, "iso_3_code": "rar", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1803", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Rakahanga-Manihiki", "depth": 14, "iso_1_code": null, "iso_3_code": "rkh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1804", "native_tokenizers": [], "scripts": [] }, { "name": "Moriori", "depth": 14, "iso_1_code": null, "iso_3_code": "rrm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1805", "native_tokenizers": [], "scripts": [] }, { "name": "Tahitian", "depth": 14, "iso_1_code": "ty", "iso_3_code": "tah", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1806", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1798", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1791", "native_tokenizers": [], "scripts": [] }, { "name": "Rapanui", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rapa Nui", "depth": 13, "iso_1_code": null, "iso_3_code": "rap", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1808", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1807", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1790", "native_tokenizers": [], "scripts": [] }, { "name": "Samoic-Outlier", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Uvean-Niuafo\u2019ou", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Niuatoputapu", "depth": 13, "iso_1_code": null, "iso_3_code": "nkp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1811", "native_tokenizers": [], "scripts": [] }, { "name": "Niuafo\u2019ou", "depth": 13, "iso_1_code": null, "iso_3_code": "num", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1812", "native_tokenizers": [], "scripts": [] }, { "name": "Wallisian", "depth": 13, "iso_1_code": null, "iso_3_code": "wls", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1813", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1810", "native_tokenizers": [], "scripts": [] }, { "name": "Ellicean", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kapingamarangi", "depth": 13, "iso_1_code": null, "iso_3_code": "kpg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1815", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Takuu", "depth": 13, "iso_1_code": null, "iso_3_code": "nho", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1816", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Nukuoro", "depth": 13, "iso_1_code": null, "iso_3_code": "nkr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1817", "native_tokenizers": [], "scripts": [] }, { "name": "Nukumanu", "depth": 13, "iso_1_code": null, "iso_3_code": "nuq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1818", "native_tokenizers": [], "scripts": [] }, { "name": "Nukeria", "depth": 13, "iso_1_code": null, "iso_3_code": "nur", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1819", "native_tokenizers": [], "scripts": [] }, { "name": "Ontong Java", "depth": 13, "iso_1_code": null, "iso_3_code": "ojv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1820", "native_tokenizers": [], "scripts": [] }, { "name": "Sikaiana", "depth": 13, "iso_1_code": null, "iso_3_code": "sky", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1821", "native_tokenizers": [], "scripts": [] }, { "name": "Tuvaluan", "depth": 13, "iso_1_code": null, "iso_3_code": "tvl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1822", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1814", "native_tokenizers": [], "scripts": [] }, { "name": "Futunic", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Anuta", "depth": 13, "iso_1_code": null, "iso_3_code": "aud", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1824", "native_tokenizers": [], "scripts": [] }, { "name": "Futuna, East", "depth": 13, "iso_1_code": null, "iso_3_code": "fud", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1825", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Futuna-Aniwa", "depth": 13, "iso_1_code": null, "iso_3_code": "fut", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1826", "native_tokenizers": [], "scripts": [] }, { "name": "Emae", "depth": 13, "iso_1_code": null, "iso_3_code": "mmw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1827", "native_tokenizers": [], "scripts": [] }, { "name": "Rennell-Bellona", "depth": 13, "iso_1_code": null, "iso_3_code": "mnv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1828", "native_tokenizers": [], "scripts": [] }, { "name": "Mele-Fila", "depth": 13, "iso_1_code": null, "iso_3_code": "mxe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1829", "native_tokenizers": [], "scripts": [] }, { "name": "Vaeakau-Taumako", "depth": 13, "iso_1_code": null, "iso_3_code": "piv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1830", "native_tokenizers": [], "scripts": [] }, { "name": "Tikopia", "depth": 13, "iso_1_code": null, "iso_3_code": "tkp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1831", "native_tokenizers": [], "scripts": [] }, { "name": "Fagauvea", "depth": 13, "iso_1_code": null, "iso_3_code": "uve", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1832", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1823", "native_tokenizers": [], "scripts": [] }, { "name": "Pukapuka", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pukapuka", "depth": 13, "iso_1_code": null, "iso_3_code": "pkp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1834", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1833", "native_tokenizers": [], "scripts": [] }, { "name": "Samoan", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Samoan", "depth": 13, "iso_1_code": "sm", "iso_3_code": "smo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1836", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1835", "native_tokenizers": [], "scripts": [] }, { "name": "Tokelauan", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tokelauan", "depth": 13, "iso_1_code": null, "iso_3_code": "tkl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1838", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1837", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1809", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1789", "native_tokenizers": [], "scripts": [] }, { "name": "Tongic", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Niue", "depth": 11, "iso_1_code": null, "iso_3_code": "niu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1840", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tongan", "depth": 11, "iso_1_code": "to", "iso_3_code": "ton", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1841", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1839", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1788", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1782", "native_tokenizers": [], "scripts": [] }, { "name": "West Fijian-Rotuman", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rotuman", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rotuman", "depth": 10, "iso_1_code": null, "iso_3_code": "rtm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1844", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1843", "native_tokenizers": [], "scripts": [] }, { "name": "West Fijian", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Namosi-Naitasiri-Serua", "depth": 10, "iso_1_code": null, "iso_3_code": "bwb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1846", "native_tokenizers": [], "scripts": [] }, { "name": "Fijian, Western", "depth": 10, "iso_1_code": null, "iso_3_code": "wyy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1847", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1845", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1842", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1781", "native_tokenizers": [], "scripts": [] }, { "name": "Loyalty Islands", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Drehu", "depth": 8, "iso_1_code": null, "iso_3_code": "dhv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1849", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Iaai", "depth": 8, "iso_1_code": null, "iso_3_code": "iai", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1850", "native_tokenizers": [], "scripts": [] }, { "name": "Nengone", "depth": 8, "iso_1_code": null, "iso_3_code": "nen", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1851", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1848", "native_tokenizers": [], "scripts": [] }, { "name": "Micronesian", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Micronesian Proper", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ikiribati", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kiribati", "depth": 10, "iso_1_code": null, "iso_3_code": "gil", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1855", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1854", "native_tokenizers": [], "scripts": [] }, { "name": "Kusaiean", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kosraean", "depth": 10, "iso_1_code": null, "iso_3_code": "kos", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1857", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1856", "native_tokenizers": [], "scripts": [] }, { "name": "Marshallese", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Marshallese", "depth": 10, "iso_1_code": "mh", "iso_3_code": "mah", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1859", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1858", "native_tokenizers": [], "scripts": [] }, { "name": "Pohnpeic-Chuukic", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chuukic", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Carolinian", "depth": 11, "iso_1_code": null, "iso_3_code": "cal", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1862", "native_tokenizers": [], "scripts": [] }, { "name": "Chuukese", "depth": 11, "iso_1_code": null, "iso_3_code": "chk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1863", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Mapia", "depth": 11, "iso_1_code": null, "iso_3_code": "mpy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1864", "native_tokenizers": [], "scripts": [] }, { "name": "Mortlockese", "depth": 11, "iso_1_code": null, "iso_3_code": "mrl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1865", "native_tokenizers": [], "scripts": [] }, { "name": "Namonuito", "depth": 11, "iso_1_code": null, "iso_3_code": "nmt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1866", "native_tokenizers": [], "scripts": [] }, { "name": "P\u00e1\u00e1fang", "depth": 11, "iso_1_code": null, "iso_3_code": "pfa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1867", "native_tokenizers": [], "scripts": [] }, { "name": "Puluwatese", "depth": 11, "iso_1_code": null, "iso_3_code": "puw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1868", "native_tokenizers": [], "scripts": [] }, { "name": "Sonsorolese", "depth": 11, "iso_1_code": null, "iso_3_code": "sov", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1869", "native_tokenizers": [], "scripts": [] }, { "name": "Satawalese", "depth": 11, "iso_1_code": null, "iso_3_code": "stw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1870", "native_tokenizers": [], "scripts": [] }, { "name": "Tobian", "depth": 11, "iso_1_code": null, "iso_3_code": "tox", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1871", "native_tokenizers": [], "scripts": [] }, { "name": "Tanapag", "depth": 11, "iso_1_code": null, "iso_3_code": "tpv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1872", "native_tokenizers": [], "scripts": [] }, { "name": "Ulithian", "depth": 11, "iso_1_code": null, "iso_3_code": "uli", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1873", "native_tokenizers": [], "scripts": [] }, { "name": "Woleaian", "depth": 11, "iso_1_code": null, "iso_3_code": "woe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1874", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1861", "native_tokenizers": [], "scripts": [] }, { "name": "Pohnpeic", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mokilese", "depth": 11, "iso_1_code": null, "iso_3_code": "mkj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1876", "native_tokenizers": [], "scripts": [] }, { "name": "Pingelapese", "depth": 11, "iso_1_code": null, "iso_3_code": "pif", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1877", "native_tokenizers": [], "scripts": [] }, { "name": "Pohnpeian", "depth": 11, "iso_1_code": null, "iso_3_code": "pon", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1878", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1875", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1860", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1853", "native_tokenizers": [], "scripts": [] }, { "name": "Nauruan", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nauruan", "depth": 9, "iso_1_code": "na", "iso_3_code": "nau", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1880", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1879", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1852", "native_tokenizers": [], "scripts": [] }, { "name": "New Caledonian", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Haekic", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Haeke", "depth": 9, "iso_1_code": null, "iso_3_code": "aek", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1883", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1882", "native_tokenizers": [], "scripts": [] }, { "name": "Northern", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Haveke", "depth": 9, "iso_1_code": null, "iso_3_code": "hvk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1885", "native_tokenizers": [], "scripts": [] }, { "name": "Vamale", "depth": 9, "iso_1_code": null, "iso_3_code": "mkt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1886", "native_tokenizers": [], "scripts": [] }, { "name": "Central", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cemuh\u00ee", "depth": 10, "iso_1_code": null, "iso_3_code": "cam", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1888", "native_tokenizers": [], "scripts": [] }, { "name": "Paic\u00ee", "depth": 10, "iso_1_code": null, "iso_3_code": "pri", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1889", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1887", "native_tokenizers": [], "scripts": [] }, { "name": "Extreme Northern", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Caac", "depth": 10, "iso_1_code": null, "iso_3_code": "msq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1891", "native_tokenizers": [], "scripts": [] }, { "name": "N\u00eal\u00eamwa-Nixumwak", "depth": 10, "iso_1_code": null, "iso_3_code": "nee", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1892", "native_tokenizers": [], "scripts": [] }, { "name": "Yuanga", "depth": 10, "iso_1_code": null, "iso_3_code": "nua", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1893", "native_tokenizers": [], "scripts": [] }, { "name": "Nyel\u00e2yu", "depth": 10, "iso_1_code": null, "iso_3_code": "yly", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1894", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1890", "native_tokenizers": [], "scripts": [] }, { "name": "North", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pwaamei", "depth": 10, "iso_1_code": null, "iso_3_code": "pme", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1896", "native_tokenizers": [], "scripts": [] }, { "name": "Pwapw\u00e2", "depth": 10, "iso_1_code": null, "iso_3_code": "pop", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1897", "native_tokenizers": [], "scripts": [] }, { "name": "Hmwaveke", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bwatoo", "depth": 11, "iso_1_code": null, "iso_3_code": "bwa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1899", "native_tokenizers": [], "scripts": [] }, { "name": "Hmwaveke", "depth": 11, "iso_1_code": null, "iso_3_code": "mrk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1900", "native_tokenizers": [], "scripts": [] }, { "name": "Waamwang", "depth": 11, "iso_1_code": null, "iso_3_code": "wmn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1901", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1898", "native_tokenizers": [], "scripts": [] }, { "name": "Nemi", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Fw\u00e2i", "depth": 11, "iso_1_code": null, "iso_3_code": "fwa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1903", "native_tokenizers": [], "scripts": [] }, { "name": "Jawe", "depth": 11, "iso_1_code": null, "iso_3_code": "jaz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1904", "native_tokenizers": [], "scripts": [] }, { "name": "Nemi", "depth": 11, "iso_1_code": null, "iso_3_code": "nem", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1905", "native_tokenizers": [], "scripts": [] }, { "name": "Pije", "depth": 11, "iso_1_code": null, "iso_3_code": "piz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1906", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1902", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1895", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1884", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Extreme Southern", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Drubea", "depth": 10, "iso_1_code": null, "iso_3_code": "duf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1909", "native_tokenizers": [], "scripts": [] }, { "name": "Num\u00e8\u00e8", "depth": 10, "iso_1_code": null, "iso_3_code": "kdk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1910", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1908", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Wailic", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aji\u00eb", "depth": 11, "iso_1_code": null, "iso_3_code": "aji", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1913", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Arh\u00f6", "depth": 11, "iso_1_code": null, "iso_3_code": "aok", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1914", "native_tokenizers": [], "scripts": [] }, { "name": "Arh\u00e2", "depth": 11, "iso_1_code": null, "iso_3_code": "aqr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1915", "native_tokenizers": [], "scripts": [] }, { "name": "Orowe", "depth": 11, "iso_1_code": null, "iso_3_code": "bpk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1916", "native_tokenizers": [], "scripts": [] }, { "name": "Neku", "depth": 11, "iso_1_code": null, "iso_3_code": "nek", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1917", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1912", "native_tokenizers": [], "scripts": [] }, { "name": "Xaracuu-Xaragure", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "X\u00e2r\u00e2c\u00f9\u00f9", "depth": 11, "iso_1_code": null, "iso_3_code": "ane", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1919", "native_tokenizers": [], "scripts": [] }, { "name": "X\u00e2r\u00e2gur\u00e8", "depth": 11, "iso_1_code": null, "iso_3_code": "axx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1920", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1918", "native_tokenizers": [], "scripts": [] }, { "name": "Zire-Tiri", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "T\u00eer\u00ee", "depth": 11, "iso_1_code": null, "iso_3_code": "cir", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1922", "native_tokenizers": [], "scripts": [] }, { "name": "S\u00eesh\u00eb\u00eb", "depth": 11, "iso_1_code": null, "iso_3_code": "sih", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1923", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1921", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1911", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1907", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1881", "native_tokenizers": [], "scripts": [] }, { "name": "North and Central Vanuatu", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Santo", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "N\u2019kep", "depth": 10, "iso_1_code": null, "iso_3_code": "sku", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1927", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1926", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Butmas-Tur", "depth": 10, "iso_1_code": null, "iso_3_code": "bnr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1929", "native_tokenizers": [], "scripts": [] }, { "name": "Lorediakarkar", "depth": 10, "iso_1_code": null, "iso_3_code": "lnn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1930", "native_tokenizers": [], "scripts": [] }, { "name": "Atin", "depth": 10, "iso_1_code": null, "iso_3_code": "plb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1931", "native_tokenizers": [], "scripts": [] }, { "name": "Ngen", "depth": 10, "iso_1_code": null, "iso_3_code": "ssv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1932", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1928", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1925", "native_tokenizers": [], "scripts": [] }, { "name": "Malekula Interior", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Labo", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ninde", "depth": 10, "iso_1_code": null, "iso_3_code": "mwi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1935", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1934", "native_tokenizers": [], "scripts": [] }, { "name": "Malekula Central", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Neverver", "depth": 10, "iso_1_code": null, "iso_3_code": "lgk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1937", "native_tokenizers": [], "scripts": [] }, { "name": "Larevat", "depth": 10, "iso_1_code": null, "iso_3_code": "lrv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1938", "native_tokenizers": [], "scripts": [] }, { "name": "Litzlitz", "depth": 10, "iso_1_code": null, "iso_3_code": "lzl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1939", "native_tokenizers": [], "scripts": [] }, { "name": "Maragus", "depth": 10, "iso_1_code": null, "iso_3_code": "mrs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1940", "native_tokenizers": [], "scripts": [] }, { "name": "V\u2019\u00ebnen Taut", "depth": 10, "iso_1_code": null, "iso_3_code": "nmb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1941", "native_tokenizers": [], "scripts": [] }, { "name": "Nasarian", "depth": 10, "iso_1_code": null, "iso_3_code": "nvh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1942", "native_tokenizers": [], "scripts": [] }, { "name": "Avava", "depth": 10, "iso_1_code": null, "iso_3_code": "tmb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1943", "native_tokenizers": [], "scripts": [] }, { "name": "Neve\u2019ei", "depth": 10, "iso_1_code": null, "iso_3_code": "vnm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1944", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1936", "native_tokenizers": [], "scripts": [] }, { "name": "Small Nambas", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dixon Reef", "depth": 10, "iso_1_code": null, "iso_3_code": "dix", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1946", "native_tokenizers": [], "scripts": [] }, { "name": "Letemboi", "depth": 10, "iso_1_code": null, "iso_3_code": "nms", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1947", "native_tokenizers": [], "scripts": [] }, { "name": "Repanbitip", "depth": 10, "iso_1_code": null, "iso_3_code": "rpn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1948", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1945", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1933", "native_tokenizers": [], "scripts": [] }, { "name": "Northeast Vanuatu-Banks Islands", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Vanuatu", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Efate, South", "depth": 10, "iso_1_code": null, "iso_3_code": "erk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1951", "native_tokenizers": [], "scripts": [] }, { "name": "Eton", "depth": 10, "iso_1_code": null, "iso_3_code": "etn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1952", "native_tokenizers": [], "scripts": [] }, { "name": "Efate, North", "depth": 10, "iso_1_code": null, "iso_3_code": "llp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1953", "native_tokenizers": [], "scripts": [] }, { "name": "Lelepa", "depth": 10, "iso_1_code": null, "iso_3_code": "lpa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1954", "native_tokenizers": [], "scripts": [] }, { "name": "Namakura", "depth": 10, "iso_1_code": null, "iso_3_code": "nmk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1955", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1950", "native_tokenizers": [], "scripts": [] }, { "name": "East Vanuatu", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Apma", "depth": 10, "iso_1_code": null, "iso_3_code": "app", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1957", "native_tokenizers": [], "scripts": [] }, { "name": "Daakaka", "depth": 10, "iso_1_code": null, "iso_3_code": "bpa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1958", "native_tokenizers": [], "scripts": [] }, { "name": "Baetora", "depth": 10, "iso_1_code": null, "iso_3_code": "btr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1959", "native_tokenizers": [], "scripts": [] }, { "name": "Lonwolwol", "depth": 10, "iso_1_code": null, "iso_3_code": "crc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1960", "native_tokenizers": [], "scripts": [] }, { "name": "Fanbak", "depth": 10, "iso_1_code": null, "iso_3_code": "fnb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1961", "native_tokenizers": [], "scripts": [] }, { "name": "Hiw", "depth": 10, "iso_1_code": null, "iso_3_code": "hiw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1962", "native_tokenizers": [], "scripts": [] }, { "name": "Koro", "depth": 10, "iso_1_code": null, "iso_3_code": "krf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1963", "native_tokenizers": [], "scripts": [] }, { "name": "Lo-Toga", "depth": 10, "iso_1_code": null, "iso_3_code": "lht", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1964", "native_tokenizers": [], "scripts": [] }, { "name": "Lakon", "depth": 10, "iso_1_code": null, "iso_3_code": "lkn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1965", "native_tokenizers": [], "scripts": [] }, { "name": "Hano", "depth": 10, "iso_1_code": null, "iso_3_code": "lml", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1966", "native_tokenizers": [], "scripts": [] }, { "name": "Lemerig", "depth": 10, "iso_1_code": null, "iso_3_code": "lrz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1967", "native_tokenizers": [], "scripts": [] }, { "name": "Mwotlap", "depth": 10, "iso_1_code": null, "iso_3_code": "mlv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1968", "native_tokenizers": [], "scripts": [] }, { "name": "Ambrym, North", "depth": 10, "iso_1_code": null, "iso_3_code": "mmg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1969", "native_tokenizers": [], "scripts": [] }, { "name": "Marino", "depth": 10, "iso_1_code": null, "iso_3_code": "mrb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1970", "native_tokenizers": [], "scripts": [] }, { "name": "Mwerlap", "depth": 10, "iso_1_code": null, "iso_3_code": "mrm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1971", "native_tokenizers": [], "scripts": [] }, { "name": "Vur\u00ebs", "depth": 10, "iso_1_code": null, "iso_3_code": "msn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1972", "native_tokenizers": [], "scripts": [] }, { "name": "Mota", "depth": 10, "iso_1_code": null, "iso_3_code": "mtt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1973", "native_tokenizers": [], "scripts": [] }, { "name": "Maewo, Central", "depth": 10, "iso_1_code": null, "iso_3_code": "mwo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1974", "native_tokenizers": [], "scripts": [] }, { "name": "Ambae, West", "depth": 10, "iso_1_code": null, "iso_3_code": "nnd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1975", "native_tokenizers": [], "scripts": [] }, { "name": "Olrat", "depth": 10, "iso_1_code": null, "iso_3_code": "olr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1976", "native_tokenizers": [], "scripts": [] }, { "name": "Ambae, East", "depth": 10, "iso_1_code": null, "iso_3_code": "omb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1977", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Paama", "depth": 10, "iso_1_code": null, "iso_3_code": "pma", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1978", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Port Vato", "depth": 10, "iso_1_code": null, "iso_3_code": "ptv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1979", "native_tokenizers": [], "scripts": [] }, { "name": "Sa", "depth": 10, "iso_1_code": null, "iso_3_code": "sax", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1980", "native_tokenizers": [], "scripts": [] }, { "name": "Ske", "depth": 10, "iso_1_code": null, "iso_3_code": "ske", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1981", "native_tokenizers": [], "scripts": [] }, { "name": "Sowa", "depth": 10, "iso_1_code": null, "iso_3_code": "sww", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1982", "native_tokenizers": [], "scripts": [] }, { "name": "Nume", "depth": 10, "iso_1_code": null, "iso_3_code": "tgs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1983", "native_tokenizers": [], "scripts": [] }, { "name": "Lehali", "depth": 10, "iso_1_code": null, "iso_3_code": "tql", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1984", "native_tokenizers": [], "scripts": [] }, { "name": "Ambrym, Southeast", "depth": 10, "iso_1_code": null, "iso_3_code": "tvk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1985", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "L\u00f6y\u00f6p", "depth": 10, "iso_1_code": null, "iso_3_code": "urr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1986", "native_tokenizers": [], "scripts": [] }, { "name": "Vera\u2019a", "depth": 10, "iso_1_code": null, "iso_3_code": "vra", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1987", "native_tokenizers": [], "scripts": [] }, { "name": "Dorig", "depth": 10, "iso_1_code": null, "iso_3_code": "wwo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1988", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1956", "native_tokenizers": [], "scripts": [] }, { "name": "Epi", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bieria-Maii", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bieria", "depth": 11, "iso_1_code": null, "iso_3_code": "brj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1991", "native_tokenizers": [], "scripts": [] }, { "name": "Maii", "depth": 11, "iso_1_code": null, "iso_3_code": "mmm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1992", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1990", "native_tokenizers": [], "scripts": [] }, { "name": "Lamenu-Baki", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Baki-Bierebo", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Baki", "depth": 12, "iso_1_code": null, "iso_3_code": "bki", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1995", "native_tokenizers": [], "scripts": [] }, { "name": "Bierebo", "depth": 12, "iso_1_code": null, "iso_3_code": "bnk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1996", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1994", "native_tokenizers": [], "scripts": [] }, { "name": "Lamenu-Lewo", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lamenu", "depth": 12, "iso_1_code": null, "iso_3_code": "lmu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "1998", "native_tokenizers": [], "scripts": [] }, { "name": "Lewo", "depth": 12, "iso_1_code": null, "iso_3_code": "lww", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1999", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1997", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1993", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1989", "native_tokenizers": [], "scripts": [] }, { "name": "Malekula Coastal", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Axamb", "depth": 10, "iso_1_code": null, "iso_3_code": "ahb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2001", "native_tokenizers": [], "scripts": [] }, { "name": "Aulua", "depth": 10, "iso_1_code": null, "iso_3_code": "aul", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2002", "native_tokenizers": [], "scripts": [] }, { "name": "Maskelynes", "depth": 10, "iso_1_code": null, "iso_3_code": "klv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2003", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Malua Bay", "depth": 10, "iso_1_code": null, "iso_3_code": "mll", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2004", "native_tokenizers": [], "scripts": [] }, { "name": "Na\u2019ahai", "depth": 10, "iso_1_code": null, "iso_3_code": "mlx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2005", "native_tokenizers": [], "scripts": [] }, { "name": "Mae", "depth": 10, "iso_1_code": null, "iso_3_code": "mme", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2006", "native_tokenizers": [], "scripts": [] }, { "name": "Mpotovoro", "depth": 10, "iso_1_code": null, "iso_3_code": "mvt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2007", "native_tokenizers": [], "scripts": [] }, { "name": "Unua", "depth": 10, "iso_1_code": null, "iso_3_code": "onu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2008", "native_tokenizers": [], "scripts": [] }, { "name": "Rerep", "depth": 10, "iso_1_code": null, "iso_3_code": "pgk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2009", "native_tokenizers": [], "scripts": [] }, { "name": "Port Sandwich", "depth": 10, "iso_1_code": null, "iso_3_code": "psw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2010", "native_tokenizers": [], "scripts": [] }, { "name": "Nahavaq", "depth": 10, "iso_1_code": null, "iso_3_code": "sns", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2011", "native_tokenizers": [], "scripts": [] }, { "name": "Uripiv-Wala-Rano-Atchin", "depth": 10, "iso_1_code": null, "iso_3_code": "upv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2012", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Vao", "depth": 10, "iso_1_code": null, "iso_3_code": "vao", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2013", "native_tokenizers": [], "scripts": [] }, { "name": "Banam Bay", "depth": 10, "iso_1_code": null, "iso_3_code": "vrt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2014", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2000", "native_tokenizers": [], "scripts": [] }, { "name": "West Santo", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Soro-n Raki", "depth": 10, "iso_1_code": null, "iso_3_code": "akr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2016", "native_tokenizers": [], "scripts": [] }, { "name": "Amblong", "depth": 10, "iso_1_code": null, "iso_3_code": "alm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2017", "native_tokenizers": [], "scripts": [] }, { "name": "Aore", "depth": 10, "iso_1_code": null, "iso_3_code": "aor", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2018", "native_tokenizers": [], "scripts": [] }, { "name": "Kiae", "depth": 10, "iso_1_code": null, "iso_3_code": "frt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2019", "native_tokenizers": [], "scripts": [] }, { "name": "Merei", "depth": 10, "iso_1_code": null, "iso_3_code": "lmb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2020", "native_tokenizers": [], "scripts": [] }, { "name": "Mafea", "depth": 10, "iso_1_code": null, "iso_3_code": "mkv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2021", "native_tokenizers": [], "scripts": [] }, { "name": "Malo", "depth": 10, "iso_1_code": null, "iso_3_code": "mla", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2022", "native_tokenizers": [], "scripts": [] }, { "name": "Tiale", "depth": 10, "iso_1_code": null, "iso_3_code": "mnl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2023", "native_tokenizers": [], "scripts": [] }, { "name": "Morouas", "depth": 10, "iso_1_code": null, "iso_3_code": "mrp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2024", "native_tokenizers": [], "scripts": [] }, { "name": "Tanokuku", "depth": 10, "iso_1_code": null, "iso_3_code": "nkk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2025", "native_tokenizers": [], "scripts": [] }, { "name": "Varsaf", "depth": 10, "iso_1_code": null, "iso_3_code": "nrg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2026", "native_tokenizers": [], "scripts": [] }, { "name": "Balen", "depth": 10, "iso_1_code": null, "iso_3_code": "nsw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2027", "native_tokenizers": [], "scripts": [] }, { "name": "Tapiafaru", "depth": 10, "iso_1_code": null, "iso_3_code": "ptr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2028", "native_tokenizers": [], "scripts": [] }, { "name": "Mores", "depth": 10, "iso_1_code": null, "iso_3_code": "rga", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2029", "native_tokenizers": [], "scripts": [] }, { "name": "Tangoa", "depth": 10, "iso_1_code": null, "iso_3_code": "tgp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2030", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tolomako", "depth": 10, "iso_1_code": null, "iso_3_code": "tlm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2031", "native_tokenizers": [], "scripts": [] }, { "name": "Tambotalo", "depth": 10, "iso_1_code": null, "iso_3_code": "tls", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2032", "native_tokenizers": [], "scripts": [] }, { "name": "Vinekula", "depth": 10, "iso_1_code": null, "iso_3_code": "tmi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2033", "native_tokenizers": [], "scripts": [] }, { "name": "Oa", "depth": 10, "iso_1_code": null, "iso_3_code": "tmt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2034", "native_tokenizers": [], "scripts": [] }, { "name": "Akei", "depth": 10, "iso_1_code": null, "iso_3_code": "tsr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2035", "native_tokenizers": [], "scripts": [] }, { "name": "Tavanlav", "depth": 10, "iso_1_code": null, "iso_3_code": "vlp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2036", "native_tokenizers": [], "scripts": [] }, { "name": "Tapesena", "depth": 10, "iso_1_code": null, "iso_3_code": "vnp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2037", "native_tokenizers": [], "scripts": [] }, { "name": "Moiso", "depth": 10, "iso_1_code": null, "iso_3_code": "wlr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2038", "native_tokenizers": [], "scripts": [] }, { "name": "Jo", "depth": 10, "iso_1_code": null, "iso_3_code": "wsi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2039", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2015", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1949", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1924", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1780", "native_tokenizers": [], "scripts": [] }, { "name": "South Vanuatu", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aneityum", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aneityum", "depth": 8, "iso_1_code": null, "iso_3_code": "aty", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2042", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2041", "native_tokenizers": [], "scripts": [] }, { "name": "Erromanga", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sie", "depth": 8, "iso_1_code": null, "iso_3_code": "erg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2044", "native_tokenizers": [], "scripts": [] }, { "name": "Ifo", "depth": 8, "iso_1_code": null, "iso_3_code": "iff", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2045", "native_tokenizers": [], "scripts": [] }, { "name": "Ura", "depth": 8, "iso_1_code": null, "iso_3_code": "uur", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2046", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2043", "native_tokenizers": [], "scripts": [] }, { "name": "Tanna", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tanna, Southwest", "depth": 8, "iso_1_code": null, "iso_3_code": "nwi", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2048", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kwamera", "depth": 8, "iso_1_code": null, "iso_3_code": "tnk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2049", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lenakel", "depth": 8, "iso_1_code": null, "iso_3_code": "tnl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2050", "native_tokenizers": [], "scripts": [] }, { "name": "Tanna, North", "depth": 8, "iso_1_code": null, "iso_3_code": "tnn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2051", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Whitesands", "depth": 8, "iso_1_code": null, "iso_3_code": "tnp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2052", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2047", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2040", "native_tokenizers": [], "scripts": [] }, { "name": "Southeast Solomonic", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gela-Guadalcanal", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bughotu", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bughotu", "depth": 9, "iso_1_code": null, "iso_3_code": "bgt", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2056", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2055", "native_tokenizers": [], "scripts": [] }, { "name": "Gela", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lengo", "depth": 9, "iso_1_code": null, "iso_3_code": "lgr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2058", "native_tokenizers": [], "scripts": [] }, { "name": "Gela", "depth": 9, "iso_1_code": null, "iso_3_code": "nlg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2059", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2057", "native_tokenizers": [], "scripts": [] }, { "name": "Guadalcanal", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Birao", "depth": 9, "iso_1_code": null, "iso_3_code": "brr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2061", "native_tokenizers": [], "scripts": [] }, { "name": "Ghari", "depth": 9, "iso_1_code": null, "iso_3_code": "gri", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2062", "native_tokenizers": [], "scripts": [] }, { "name": "Malango", "depth": 9, "iso_1_code": null, "iso_3_code": "mln", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2063", "native_tokenizers": [], "scripts": [] }, { "name": "Talise", "depth": 9, "iso_1_code": null, "iso_3_code": "tlr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2064", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2060", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2054", "native_tokenizers": [], "scripts": [] }, { "name": "Malaita-San Cristobal", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Malaita", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Longgu", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Longgu", "depth": 10, "iso_1_code": null, "iso_3_code": "lgu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2068", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2067", "native_tokenizers": [], "scripts": [] }, { "name": "Northern", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Baelelea", "depth": 10, "iso_1_code": null, "iso_3_code": "bvc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2070", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Baeggu", "depth": 10, "iso_1_code": null, "iso_3_code": "bvd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2071", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Fataleka", "depth": 10, "iso_1_code": null, "iso_3_code": "far", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2072", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Gula\u2019alaa", "depth": 10, "iso_1_code": null, "iso_3_code": "gmb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2073", "native_tokenizers": [], "scripts": [] }, { "name": "Kwaio", "depth": 10, "iso_1_code": null, "iso_3_code": "kwd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2074", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kwara\u2019ae", "depth": 10, "iso_1_code": null, "iso_3_code": "kwf", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2075", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Wala", "depth": 10, "iso_1_code": null, "iso_3_code": "lgl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2076", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lau", "depth": 10, "iso_1_code": null, "iso_3_code": "llu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2077", "native_tokenizers": [], "scripts": [] }, { "name": "To\u2019abaita", "depth": 10, "iso_1_code": null, "iso_3_code": "mlu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2078", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2069", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "\u2019Are\u2019are", "depth": 10, "iso_1_code": null, "iso_3_code": "alu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2080", "native_tokenizers": [], "scripts": [] }, { "name": "Sa\ua78ca", "depth": 10, "iso_1_code": null, "iso_3_code": "apb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2081", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Dori\u2019o", "depth": 10, "iso_1_code": null, "iso_3_code": "dor", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2082", "native_tokenizers": [], "scripts": [] }, { "name": "Oroha", "depth": 10, "iso_1_code": null, "iso_3_code": "ora", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2083", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2079", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2066", "native_tokenizers": [], "scripts": [] }, { "name": "San Cristobal", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kahua", "depth": 9, "iso_1_code": null, "iso_3_code": "agw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2085", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Arosi", "depth": 9, "iso_1_code": null, "iso_3_code": "aia", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2086", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bauro", "depth": 9, "iso_1_code": null, "iso_3_code": "bxa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2087", "native_tokenizers": [], "scripts": [] }, { "name": "Fagani", "depth": 9, "iso_1_code": null, "iso_3_code": "faf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2088", "native_tokenizers": [], "scripts": [] }, { "name": "Owa", "depth": 9, "iso_1_code": null, "iso_3_code": "stn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2089", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2084", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2065", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2053", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1779", "native_tokenizers": [], "scripts": [] }, { "name": "St. Matthias", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mussau-Emira", "depth": 6, "iso_1_code": null, "iso_3_code": "emi", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2091", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tenis", "depth": 6, "iso_1_code": null, "iso_3_code": "tns", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2092", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2090", "native_tokenizers": [], "scripts": [] }, { "name": "Temotu", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Reefs-Santa Cruz", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "\u00c4iwoo", "depth": 7, "iso_1_code": null, "iso_3_code": "nfl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2095", "native_tokenizers": [], "scripts": [] }, { "name": "Engdewu", "depth": 7, "iso_1_code": null, "iso_3_code": "ngr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2096", "native_tokenizers": [], "scripts": [] }, { "name": "Nal\u00f6go", "depth": 7, "iso_1_code": null, "iso_3_code": "nlz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2097", "native_tokenizers": [], "scripts": [] }, { "name": "Noip\u00e4", "depth": 7, "iso_1_code": null, "iso_3_code": "npx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2098", "native_tokenizers": [], "scripts": [] }, { "name": "Nat\u00fcgu", "depth": 7, "iso_1_code": null, "iso_3_code": "ntu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2099", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2094", "native_tokenizers": [], "scripts": [] }, { "name": "Utupua-Vanikoro", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Teanu", "depth": 7, "iso_1_code": null, "iso_3_code": "tkw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2101", "native_tokenizers": [], "scripts": [] }, { "name": "Tanema", "depth": 7, "iso_1_code": null, "iso_3_code": "tnx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2102", "native_tokenizers": [], "scripts": [] }, { "name": "Lovono", "depth": 7, "iso_1_code": null, "iso_3_code": "vnk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2103", "native_tokenizers": [], "scripts": [] }, { "name": "Utupua", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Asumboa", "depth": 8, "iso_1_code": null, "iso_3_code": "aua", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2105", "native_tokenizers": [], "scripts": [] }, { "name": "Tanibili", "depth": 8, "iso_1_code": null, "iso_3_code": "tbe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2106", "native_tokenizers": [], "scripts": [] }, { "name": "Amba", "depth": 8, "iso_1_code": null, "iso_3_code": "utp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2107", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2104", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2100", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2093", "native_tokenizers": [], "scripts": [] }, { "name": "Western Oceanic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Meso Melanesian", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bali-Vitu", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Uneapa", "depth": 8, "iso_1_code": null, "iso_3_code": "bbn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2111", "native_tokenizers": [], "scripts": [] }, { "name": "Vitu", "depth": 8, "iso_1_code": null, "iso_3_code": "wiv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2112", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2110", "native_tokenizers": [], "scripts": [] }, { "name": "New Ireland", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lavongai-Nalik", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tungag", "depth": 9, "iso_1_code": null, "iso_3_code": "lcm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2115", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kara", "depth": 9, "iso_1_code": null, "iso_3_code": "leu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2116", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lakurumau", "depth": 9, "iso_1_code": null, "iso_3_code": "lxm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2117", "native_tokenizers": [], "scripts": [] }, { "name": "Nalik", "depth": 9, "iso_1_code": null, "iso_3_code": "nal", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2118", "native_tokenizers": [], "scripts": [] }, { "name": "Mandara", "depth": 9, "iso_1_code": null, "iso_3_code": "tbf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2119", "native_tokenizers": [], "scripts": [] }, { "name": "Tiang", "depth": 9, "iso_1_code": null, "iso_3_code": "tbj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2120", "native_tokenizers": [], "scripts": [] }, { "name": "Tigak", "depth": 9, "iso_1_code": null, "iso_3_code": "tgc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2121", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2114", "native_tokenizers": [], "scripts": [] }, { "name": "Madak", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Barok", "depth": 9, "iso_1_code": null, "iso_3_code": "bjk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2123", "native_tokenizers": [], "scripts": [] }, { "name": "Lavatbura-Lamusong", "depth": 9, "iso_1_code": null, "iso_3_code": "lbv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2124", "native_tokenizers": [], "scripts": [] }, { "name": "Madak", "depth": 9, "iso_1_code": null, "iso_3_code": "mmx", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2125", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2122", "native_tokenizers": [], "scripts": [] }, { "name": "South New Ireland-Northwest Solomonic", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Minigir", "depth": 9, "iso_1_code": null, "iso_3_code": "bxf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2127", "native_tokenizers": [], "scripts": [] }, { "name": "Choiseul", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Babatana", "depth": 10, "iso_1_code": null, "iso_3_code": "baa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2129", "native_tokenizers": [], "scripts": [] }, { "name": "Ririo", "depth": 10, "iso_1_code": null, "iso_3_code": "rri", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2130", "native_tokenizers": [], "scripts": [] }, { "name": "Vaghua", "depth": 10, "iso_1_code": null, "iso_3_code": "tva", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2131", "native_tokenizers": [], "scripts": [] }, { "name": "Varisi", "depth": 10, "iso_1_code": null, "iso_3_code": "vrs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2132", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2128", "native_tokenizers": [], "scripts": [] }, { "name": "Mono-Uruava", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mono", "depth": 10, "iso_1_code": null, "iso_3_code": "mte", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2134", "native_tokenizers": [], "scripts": [] }, { "name": "Torau", "depth": 10, "iso_1_code": null, "iso_3_code": "ttu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2135", "native_tokenizers": [], "scripts": [] }, { "name": "Uruava", "depth": 10, "iso_1_code": null, "iso_3_code": "urv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2136", "native_tokenizers": [], "scripts": [] }, { "name": "Vinitiri", "depth": 10, "iso_1_code": null, "iso_3_code": "vmg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2137", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2133", "native_tokenizers": [], "scripts": [] }, { "name": "Nehan-North Bougainville", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buka", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Petats", "depth": 11, "iso_1_code": null, "iso_3_code": "pex", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2140", "native_tokenizers": [], "scripts": [] }, { "name": "Halia", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hak\u00f6", "depth": 12, "iso_1_code": null, "iso_3_code": "hao", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2142", "native_tokenizers": [], "scripts": [] }, { "name": "Halia", "depth": 12, "iso_1_code": null, "iso_3_code": "hla", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2143", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2141", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2139", "native_tokenizers": [], "scripts": [] }, { "name": "Nehan", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nehan", "depth": 11, "iso_1_code": null, "iso_3_code": "nsn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2145", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2144", "native_tokenizers": [], "scripts": [] }, { "name": "Papapana", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Papapana", "depth": 11, "iso_1_code": null, "iso_3_code": "ppn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2147", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2146", "native_tokenizers": [], "scripts": [] }, { "name": "Saposa-Tinputz", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hahon", "depth": 11, "iso_1_code": null, "iso_3_code": "hah", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2149", "native_tokenizers": [], "scripts": [] }, { "name": "Saposa", "depth": 11, "iso_1_code": null, "iso_3_code": "sps", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2150", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Teop", "depth": 11, "iso_1_code": null, "iso_3_code": "tio", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2151", "native_tokenizers": [], "scripts": [] }, { "name": "Tinputz", "depth": 11, "iso_1_code": null, "iso_3_code": "tpz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2152", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2148", "native_tokenizers": [], "scripts": [] }, { "name": "Solos", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Solos", "depth": 11, "iso_1_code": null, "iso_3_code": "sol", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2154", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2153", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2138", "native_tokenizers": [], "scripts": [] }, { "name": "New Georgia", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Vangunu", "depth": 11, "iso_1_code": null, "iso_3_code": "mpr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2157", "native_tokenizers": [], "scripts": [] }, { "name": "Marovo", "depth": 11, "iso_1_code": null, "iso_3_code": "mvo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2158", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2156", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ghanongga", "depth": 11, "iso_1_code": null, "iso_3_code": "ghn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2160", "native_tokenizers": [], "scripts": [] }, { "name": "Hoava", "depth": 11, "iso_1_code": null, "iso_3_code": "hoa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2161", "native_tokenizers": [], "scripts": [] }, { "name": "Kusaghe", "depth": 11, "iso_1_code": null, "iso_3_code": "ksg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2162", "native_tokenizers": [], "scripts": [] }, { "name": "Kazukuru", "depth": 11, "iso_1_code": null, "iso_3_code": "kzk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2163", "native_tokenizers": [], "scripts": [] }, { "name": "Lungga", "depth": 11, "iso_1_code": null, "iso_3_code": "lga", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2164", "native_tokenizers": [], "scripts": [] }, { "name": "Dughore", "depth": 11, "iso_1_code": null, "iso_3_code": "nke", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2165", "native_tokenizers": [], "scripts": [] }, { "name": "Roviana", "depth": 11, "iso_1_code": null, "iso_3_code": "rug", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2166", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Simbo", "depth": 11, "iso_1_code": null, "iso_3_code": "sbb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2167", "native_tokenizers": [], "scripts": [] }, { "name": "Ughele", "depth": 11, "iso_1_code": null, "iso_3_code": "uge", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2168", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2159", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2155", "native_tokenizers": [], "scripts": [] }, { "name": "Patpatar-Tolai", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Fanamaket", "depth": 10, "iso_1_code": null, "iso_3_code": "bjp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2170", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Patpatar", "depth": 10, "iso_1_code": null, "iso_3_code": "gfk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2171", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Guramalum", "depth": 10, "iso_1_code": null, "iso_3_code": "grz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2172", "native_tokenizers": [], "scripts": [] }, { "name": "Niwer Mil", "depth": 10, "iso_1_code": null, "iso_3_code": "hrc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2173", "native_tokenizers": [], "scripts": [] }, { "name": "Warwar Feni", "depth": 10, "iso_1_code": null, "iso_3_code": "hrw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2174", "native_tokenizers": [], "scripts": [] }, { "name": "Konomala", "depth": 10, "iso_1_code": null, "iso_3_code": "koa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2175", "native_tokenizers": [], "scripts": [] }, { "name": "Kandas", "depth": 10, "iso_1_code": null, "iso_3_code": "kqw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2176", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kuanua", "depth": 10, "iso_1_code": null, "iso_3_code": "ksd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2177", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Label", "depth": 10, "iso_1_code": null, "iso_3_code": "lbb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2178", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ramoaaina", "depth": 10, "iso_1_code": null, "iso_3_code": "rai", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2179", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sursurunga", "depth": 10, "iso_1_code": null, "iso_3_code": "sgz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2180", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Siar-Lak", "depth": 10, "iso_1_code": null, "iso_3_code": "sjr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2181", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2169", "native_tokenizers": [], "scripts": [] }, { "name": "Piva-Banoni", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bannoni", "depth": 10, "iso_1_code": null, "iso_3_code": "bcm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2183", "native_tokenizers": [], "scripts": [] }, { "name": "Lawunuia", "depth": 10, "iso_1_code": null, "iso_3_code": "tgi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2184", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2182", "native_tokenizers": [], "scripts": [] }, { "name": "Santa Isabel", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Blablanga", "depth": 11, "iso_1_code": null, "iso_3_code": "blp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2187", "native_tokenizers": [], "scripts": [] }, { "name": "Zazao", "depth": 11, "iso_1_code": null, "iso_3_code": "jaj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2188", "native_tokenizers": [], "scripts": [] }, { "name": "Kokota", "depth": 11, "iso_1_code": null, "iso_3_code": "kkk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2189", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2186", "native_tokenizers": [], "scripts": [] }, { "name": "East", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gao", "depth": 11, "iso_1_code": null, "iso_3_code": "gga", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2191", "native_tokenizers": [], "scripts": [] }, { "name": "Cheke Holo", "depth": 11, "iso_1_code": null, "iso_3_code": "mrn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2192", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2190", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Zabana", "depth": 11, "iso_1_code": null, "iso_3_code": "kji", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2194", "native_tokenizers": [], "scripts": [] }, { "name": "Laghu", "depth": 11, "iso_1_code": null, "iso_3_code": "lgb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2195", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2193", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2185", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2126", "native_tokenizers": [], "scripts": [] }, { "name": "Tabar", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lihir", "depth": 9, "iso_1_code": null, "iso_3_code": "lih", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2197", "native_tokenizers": [], "scripts": [] }, { "name": "Notsi", "depth": 9, "iso_1_code": null, "iso_3_code": "ncf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2198", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2196", "native_tokenizers": [], "scripts": [] }, { "name": "Tomoip", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tomoip", "depth": 9, "iso_1_code": null, "iso_3_code": "tqp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2200", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2199", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2113", "native_tokenizers": [], "scripts": [] }, { "name": "Willaumez", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bulu", "depth": 8, "iso_1_code": null, "iso_3_code": "bjl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2202", "native_tokenizers": [], "scripts": [] }, { "name": "Bola", "depth": 8, "iso_1_code": null, "iso_3_code": "bnp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2203", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Meramera", "depth": 8, "iso_1_code": null, "iso_3_code": "mxm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2204", "native_tokenizers": [], "scripts": [] }, { "name": "Nakanai", "depth": 8, "iso_1_code": null, "iso_3_code": "nak", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2205", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2201", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2109", "native_tokenizers": [], "scripts": [] }, { "name": "North New Guinea", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Huon Gulf", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Markham", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lower", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Busu", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Duwet", "depth": 11, "iso_1_code": null, "iso_3_code": "gve", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2211", "native_tokenizers": [], "scripts": [] }, { "name": "Aribwatsa", "depth": 11, "iso_1_code": null, "iso_3_code": "laz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2212", "native_tokenizers": [], "scripts": [] }, { "name": "Musom", "depth": 11, "iso_1_code": null, "iso_3_code": "msu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2213", "native_tokenizers": [], "scripts": [] }, { "name": "Nafi", "depth": 11, "iso_1_code": null, "iso_3_code": "srf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2214", "native_tokenizers": [], "scripts": [] }, { "name": "Aribwaung", "depth": 11, "iso_1_code": null, "iso_3_code": "ylu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2215", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2210", "native_tokenizers": [], "scripts": [] }, { "name": "Labu", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Labu", "depth": 11, "iso_1_code": null, "iso_3_code": "lbu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2217", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2216", "native_tokenizers": [], "scripts": [] }, { "name": "Wampar", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Wampar", "depth": 11, "iso_1_code": null, "iso_3_code": "lbq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2219", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2218", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2209", "native_tokenizers": [], "scripts": [] }, { "name": "Upper", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Adzera", "depth": 10, "iso_1_code": null, "iso_3_code": "adz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2221", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Mountain", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mari", "depth": 11, "iso_1_code": null, "iso_3_code": "hob", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2223", "native_tokenizers": [], "scripts": [] }, { "name": "Wampur", "depth": 11, "iso_1_code": null, "iso_3_code": "waz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2224", "native_tokenizers": [], "scripts": [] }, { "name": "Sarasira", "depth": 11, "iso_1_code": null, "iso_3_code": "zsa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2225", "native_tokenizers": [], "scripts": [] }, { "name": "Sukurum", "depth": 11, "iso_1_code": null, "iso_3_code": "zsu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2226", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2222", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2220", "native_tokenizers": [], "scripts": [] }, { "name": "Watut", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kodut, South", "depth": 10, "iso_1_code": null, "iso_3_code": "mcy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2228", "native_tokenizers": [], "scripts": [] }, { "name": "Kodut, Middle", "depth": 10, "iso_1_code": null, "iso_3_code": "mpl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2229", "native_tokenizers": [], "scripts": [] }, { "name": "Kodut, North", "depth": 10, "iso_1_code": null, "iso_3_code": "una", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2230", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2227", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2208", "native_tokenizers": [], "scripts": [] }, { "name": "North", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bugawac", "depth": 9, "iso_1_code": null, "iso_3_code": "buk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2232", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Yabem", "depth": 9, "iso_1_code": null, "iso_3_code": "jae", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2233", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kala", "depth": 9, "iso_1_code": null, "iso_3_code": "kcl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2234", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2231", "native_tokenizers": [], "scripts": [] }, { "name": "Numbami", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Numbami", "depth": 9, "iso_1_code": null, "iso_3_code": "sij", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2236", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2235", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hote-Buang", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buang", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buang, Central", "depth": 11, "iso_1_code": null, "iso_3_code": "bzh", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2240", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Buang, Mangga", "depth": 11, "iso_1_code": null, "iso_3_code": "mmo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2241", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Piu", "depth": 11, "iso_1_code": null, "iso_3_code": "pix", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2242", "native_tokenizers": [], "scripts": [] }, { "name": "Kapin", "depth": 11, "iso_1_code": null, "iso_3_code": "tbx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2243", "native_tokenizers": [], "scripts": [] }, { "name": "Vehes", "depth": 11, "iso_1_code": null, "iso_3_code": "val", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2244", "native_tokenizers": [], "scripts": [] }, { "name": "Mumeng", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dambi", "depth": 12, "iso_1_code": null, "iso_3_code": "dac", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2246", "native_tokenizers": [], "scripts": [] }, { "name": "Gorakor", "depth": 12, "iso_1_code": null, "iso_3_code": "goc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2247", "native_tokenizers": [], "scripts": [] }, { "name": "Kumalu", "depth": 12, "iso_1_code": null, "iso_3_code": "ksl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2248", "native_tokenizers": [], "scripts": [] }, { "name": "Patep", "depth": 12, "iso_1_code": null, "iso_3_code": "ptp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2249", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Zenag", "depth": 12, "iso_1_code": null, "iso_3_code": "zeg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2250", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2245", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2239", "native_tokenizers": [], "scripts": [] }, { "name": "Hote", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Malei", "depth": 11, "iso_1_code": null, "iso_3_code": "hot", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2252", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Yamap", "depth": 11, "iso_1_code": null, "iso_3_code": "ymp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2253", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2251", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2238", "native_tokenizers": [], "scripts": [] }, { "name": "Kaiwa", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Iwal", "depth": 10, "iso_1_code": null, "iso_3_code": "kbm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2255", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2254", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2237", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2207", "native_tokenizers": [], "scripts": [] }, { "name": "Ngero-Vitiaz", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ngero", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bariai", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bariai", "depth": 10, "iso_1_code": null, "iso_3_code": "bch", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2259", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lusi", "depth": 10, "iso_1_code": null, "iso_3_code": "khl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2260", "native_tokenizers": [], "scripts": [] }, { "name": "Kove", "depth": 10, "iso_1_code": null, "iso_3_code": "kvc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2261", "native_tokenizers": [], "scripts": [] }, { "name": "Mala", "depth": 10, "iso_1_code": null, "iso_3_code": "mmt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2262", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2258", "native_tokenizers": [], "scripts": [] }, { "name": "Tuam", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gitua", "depth": 10, "iso_1_code": null, "iso_3_code": "ggt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2264", "native_tokenizers": [], "scripts": [] }, { "name": "Mutu", "depth": 10, "iso_1_code": null, "iso_3_code": "tuc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2265", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2263", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2257", "native_tokenizers": [], "scripts": [] }, { "name": "Vitiaz", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bel", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Astrolabe", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Awad Bing", "depth": 11, "iso_1_code": null, "iso_3_code": "bcu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2269", "native_tokenizers": [], "scripts": [] }, { "name": "Mindiri", "depth": 11, "iso_1_code": null, "iso_3_code": "mpn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2270", "native_tokenizers": [], "scripts": [] }, { "name": "Yote", "depth": 11, "iso_1_code": null, "iso_3_code": "wab", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2271", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2268", "native_tokenizers": [], "scripts": [] }, { "name": "Nuclear Bel", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northern", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bilbil", "depth": 12, "iso_1_code": null, "iso_3_code": "brz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2274", "native_tokenizers": [], "scripts": [] }, { "name": "Gedaged", "depth": 12, "iso_1_code": null, "iso_3_code": "gdd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2275", "native_tokenizers": [], "scripts": [] }, { "name": "Matukar Panau", "depth": 12, "iso_1_code": null, "iso_3_code": "mjk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2276", "native_tokenizers": [], "scripts": [] }, { "name": "Takia", "depth": 12, "iso_1_code": null, "iso_3_code": "tbc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2277", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2273", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Marik", "depth": 12, "iso_1_code": null, "iso_3_code": "dad", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2279", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2278", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2272", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2267", "native_tokenizers": [], "scripts": [] }, { "name": "Kilenge-Maleu", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Maleu-Kilenge", "depth": 10, "iso_1_code": null, "iso_3_code": "mgl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2281", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2280", "native_tokenizers": [], "scripts": [] }, { "name": "Korap", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arop-Lokep", "depth": 10, "iso_1_code": null, "iso_3_code": "apr", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2283", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Karnai", "depth": 10, "iso_1_code": null, "iso_3_code": "bbv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2284", "native_tokenizers": [], "scripts": [] }, { "name": "Pano", "depth": 10, "iso_1_code": null, "iso_3_code": "mqz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2285", "native_tokenizers": [], "scripts": [] }, { "name": "Mur Pano", "depth": 10, "iso_1_code": null, "iso_3_code": "tkv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2286", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2282", "native_tokenizers": [], "scripts": [] }, { "name": "Mangap-Mbula", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mbula", "depth": 10, "iso_1_code": null, "iso_3_code": "mna", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2288", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2287", "native_tokenizers": [], "scripts": [] }, { "name": "Mengen", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mamusi", "depth": 10, "iso_1_code": null, "iso_3_code": "kdf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2290", "native_tokenizers": [], "scripts": [] }, { "name": "Mengen", "depth": 10, "iso_1_code": null, "iso_3_code": "mee", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2291", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lote", "depth": 10, "iso_1_code": null, "iso_3_code": "uvl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2292", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2289", "native_tokenizers": [], "scripts": [] }, { "name": "Roinji-Nenaya", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mato", "depth": 10, "iso_1_code": null, "iso_3_code": "met", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2294", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Uma", "depth": 10, "iso_1_code": null, "iso_3_code": "roe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2295", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2293", "native_tokenizers": [], "scripts": [] }, { "name": "Sio", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sio", "depth": 10, "iso_1_code": null, "iso_3_code": "xsi", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2297", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2296", "native_tokenizers": [], "scripts": [] }, { "name": "Southwest New Britain", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Amara", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Amara", "depth": 11, "iso_1_code": null, "iso_3_code": "aie", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2300", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2299", "native_tokenizers": [], "scripts": [] }, { "name": "Arawe-Pasismanua", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arawe", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mangseng", "depth": 12, "iso_1_code": null, "iso_3_code": "mbh", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2303", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "East Arawe", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Akolet", "depth": 13, "iso_1_code": null, "iso_3_code": "akt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2305", "native_tokenizers": [], "scripts": [] }, { "name": "Avau", "depth": 13, "iso_1_code": null, "iso_3_code": "avb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2306", "native_tokenizers": [], "scripts": [] }, { "name": "Bebeli", "depth": 13, "iso_1_code": null, "iso_3_code": "bek", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2307", "native_tokenizers": [], "scripts": [] }, { "name": "Amio-Gelimi", "depth": 13, "iso_1_code": null, "iso_3_code": "let", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2308", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2304", "native_tokenizers": [], "scripts": [] }, { "name": "West Arawe", "depth": 12, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Solong", "depth": 13, "iso_1_code": null, "iso_3_code": "aaw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2310", "native_tokenizers": [], "scripts": [] }, { "name": "Ambul", "depth": 13, "iso_1_code": null, "iso_3_code": "apo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2311", "native_tokenizers": [], "scripts": [] }, { "name": "Gimi", "depth": 13, "iso_1_code": null, "iso_3_code": "gip", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2312", "native_tokenizers": [], "scripts": [] }, { "name": "Aiklep", "depth": 13, "iso_1_code": null, "iso_3_code": "mwg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2313", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2309", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2302", "native_tokenizers": [], "scripts": [] }, { "name": "Pasismanua", "depth": 11, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aighon", "depth": 12, "iso_1_code": null, "iso_3_code": "aix", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2315", "native_tokenizers": [], "scripts": [] }, { "name": "Miu", "depth": 12, "iso_1_code": null, "iso_3_code": "mpo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2316", "native_tokenizers": [], "scripts": [] }, { "name": "Kaulong", "depth": 12, "iso_1_code": null, "iso_3_code": "pss", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2317", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sengseng", "depth": 12, "iso_1_code": null, "iso_3_code": "ssz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2318", "native_tokenizers": [], "scripts": [] }, { "name": "Karore", "depth": 12, "iso_1_code": null, "iso_3_code": "xkx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2319", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2314", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2301", "native_tokenizers": [], "scripts": [] }, { "name": "Bibling", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lamogai", "depth": 11, "iso_1_code": null, "iso_3_code": "lmg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2321", "native_tokenizers": [], "scripts": [] }, { "name": "Mouk-Aria", "depth": 11, "iso_1_code": null, "iso_3_code": "mwh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2322", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2320", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2298", "native_tokenizers": [], "scripts": [] }, { "name": "Tami", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tami", "depth": 10, "iso_1_code": null, "iso_3_code": "tmy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2324", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2323", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2266", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2256", "native_tokenizers": [], "scripts": [] }, { "name": "Sarmi-Jayapura Bay", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jayapura Bay", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayupulau", "depth": 9, "iso_1_code": null, "iso_3_code": "kzu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2327", "native_tokenizers": [], "scripts": [] }, { "name": "Ormu", "depth": 9, "iso_1_code": null, "iso_3_code": "orz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2328", "native_tokenizers": [], "scripts": [] }, { "name": "Tobati", "depth": 9, "iso_1_code": null, "iso_3_code": "tti", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2329", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2326", "native_tokenizers": [], "scripts": [] }, { "name": "Sarmi", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Anus", "depth": 9, "iso_1_code": null, "iso_3_code": "auq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2331", "native_tokenizers": [], "scripts": [] }, { "name": "Bonggo", "depth": 9, "iso_1_code": null, "iso_3_code": "bpg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2332", "native_tokenizers": [], "scripts": [] }, { "name": "Masimasi", "depth": 9, "iso_1_code": null, "iso_3_code": "ism", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2333", "native_tokenizers": [], "scripts": [] }, { "name": "Kaptiau", "depth": 9, "iso_1_code": null, "iso_3_code": "kbi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2334", "native_tokenizers": [], "scripts": [] }, { "name": "Liki", "depth": 9, "iso_1_code": null, "iso_3_code": "lio", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2335", "native_tokenizers": [], "scripts": [] }, { "name": "Fedan", "depth": 9, "iso_1_code": null, "iso_3_code": "pdn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2336", "native_tokenizers": [], "scripts": [] }, { "name": "Sobei", "depth": 9, "iso_1_code": null, "iso_3_code": "sob", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2337", "native_tokenizers": [], "scripts": [] }, { "name": "Tarpia", "depth": 9, "iso_1_code": null, "iso_3_code": "tpf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2338", "native_tokenizers": [], "scripts": [] }, { "name": "Mo", "depth": 9, "iso_1_code": null, "iso_3_code": "wkd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2339", "native_tokenizers": [], "scripts": [] }, { "name": "Sunum", "depth": 9, "iso_1_code": null, "iso_3_code": "ymn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2340", "native_tokenizers": [], "scripts": [] }, { "name": "Yarsun", "depth": 9, "iso_1_code": null, "iso_3_code": "yrs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2341", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2330", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2325", "native_tokenizers": [], "scripts": [] }, { "name": "Schouten", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kairiru-Manam", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kairiru", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kaiep", "depth": 10, "iso_1_code": null, "iso_3_code": "kbw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2345", "native_tokenizers": [], "scripts": [] }, { "name": "Kairiru", "depth": 10, "iso_1_code": null, "iso_3_code": "kxa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2346", "native_tokenizers": [], "scripts": [] }, { "name": "Terebu", "depth": 10, "iso_1_code": null, "iso_3_code": "trb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2347", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2344", "native_tokenizers": [], "scripts": [] }, { "name": "Manam", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Biem", "depth": 10, "iso_1_code": null, "iso_3_code": "bmc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2349", "native_tokenizers": [], "scripts": [] }, { "name": "Kis", "depth": 10, "iso_1_code": null, "iso_3_code": "kis", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2350", "native_tokenizers": [], "scripts": [] }, { "name": "Medebur", "depth": 10, "iso_1_code": null, "iso_3_code": "mjm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2351", "native_tokenizers": [], "scripts": [] }, { "name": "Manam", "depth": 10, "iso_1_code": null, "iso_3_code": "mva", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2352", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sepa", "depth": 10, "iso_1_code": null, "iso_3_code": "spe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2353", "native_tokenizers": [], "scripts": [] }, { "name": "Wogeo", "depth": 10, "iso_1_code": null, "iso_3_code": "woc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2354", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2348", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2343", "native_tokenizers": [], "scripts": [] }, { "name": "Siau", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Orop", "depth": 9, "iso_1_code": null, "iso_3_code": "aps", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2356", "native_tokenizers": [], "scripts": [] }, { "name": "Malol", "depth": 9, "iso_1_code": null, "iso_3_code": "mbk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2357", "native_tokenizers": [], "scripts": [] }, { "name": "Sera", "depth": 9, "iso_1_code": null, "iso_3_code": "sry", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2358", "native_tokenizers": [], "scripts": [] }, { "name": "Essono", "depth": 9, "iso_1_code": null, "iso_3_code": "sso", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2359", "native_tokenizers": [], "scripts": [] }, { "name": "Ulau-Suain", "depth": 9, "iso_1_code": null, "iso_3_code": "svb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2360", "native_tokenizers": [], "scripts": [] }, { "name": "Tumleo", "depth": 9, "iso_1_code": null, "iso_3_code": "tmq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2361", "native_tokenizers": [], "scripts": [] }, { "name": "Kap", "depth": 9, "iso_1_code": null, "iso_3_code": "ykm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2362", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2355", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2342", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2206", "native_tokenizers": [], "scripts": [] }, { "name": "Papuan Tip", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nuclear", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Maisin", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Maisin", "depth": 9, "iso_1_code": null, "iso_3_code": "mbq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2366", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2365", "native_tokenizers": [], "scripts": [] }, { "name": "North Papuan Mainland-D\u2019Entrecasteaux", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Anuki", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Anuki", "depth": 10, "iso_1_code": null, "iso_3_code": "aui", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2369", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2368", "native_tokenizers": [], "scripts": [] }, { "name": "Are-Taupota", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Are", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Miniafia Oyan", "depth": 11, "iso_1_code": null, "iso_3_code": "aai", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2372", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ghayavi", "depth": 11, "iso_1_code": null, "iso_3_code": "bmk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2373", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Doga", "depth": 11, "iso_1_code": null, "iso_3_code": "dgg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2374", "native_tokenizers": [], "scripts": [] }, { "name": "Are", "depth": 11, "iso_1_code": null, "iso_3_code": "mwc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2375", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Gapapaiwa", "depth": 11, "iso_1_code": null, "iso_3_code": "pwg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2376", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ubir", "depth": 11, "iso_1_code": null, "iso_3_code": "ubr", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2377", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kaninuwa", "depth": 11, "iso_1_code": null, "iso_3_code": "wat", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2378", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2371", "native_tokenizers": [], "scripts": [] }, { "name": "Taupota", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gweda", "depth": 11, "iso_1_code": null, "iso_3_code": "grw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2380", "native_tokenizers": [], "scripts": [] }, { "name": "Haigwai", "depth": 11, "iso_1_code": null, "iso_3_code": "hgw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2381", "native_tokenizers": [], "scripts": [] }, { "name": "Maiwala", "depth": 11, "iso_1_code": null, "iso_3_code": "mum", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2382", "native_tokenizers": [], "scripts": [] }, { "name": "Minaveha", "depth": 11, "iso_1_code": null, "iso_3_code": "mvn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2383", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tawala", "depth": 11, "iso_1_code": null, "iso_3_code": "tbo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2384", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Taupota", "depth": 11, "iso_1_code": null, "iso_3_code": "tpa", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2385", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Wa\u2019ema", "depth": 11, "iso_1_code": null, "iso_3_code": "wag", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2386", "native_tokenizers": [], "scripts": [] }, { "name": "Wedau", "depth": 11, "iso_1_code": null, "iso_3_code": "wed", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2387", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Yakaikeke", "depth": 11, "iso_1_code": null, "iso_3_code": "ykk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2388", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2379", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2370", "native_tokenizers": [], "scripts": [] }, { "name": "Bwaidoga", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bwaidoka", "depth": 10, "iso_1_code": null, "iso_3_code": "bwd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2390", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Goodenough, West", "depth": 10, "iso_1_code": null, "iso_3_code": "ddi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2391", "native_tokenizers": [], "scripts": [] }, { "name": "Koluwawa", "depth": 10, "iso_1_code": null, "iso_3_code": "klx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2392", "native_tokenizers": [], "scripts": [] }, { "name": "Molima", "depth": 10, "iso_1_code": null, "iso_3_code": "mox", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2393", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Maiadomu", "depth": 10, "iso_1_code": null, "iso_3_code": "mzz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2394", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Iduna", "depth": 10, "iso_1_code": null, "iso_3_code": "viv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2395", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Iamalele", "depth": 10, "iso_1_code": null, "iso_3_code": "yml", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2396", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2389", "native_tokenizers": [], "scripts": [] }, { "name": "Dobu-Duau", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bunama", "depth": 10, "iso_1_code": null, "iso_3_code": "bdd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2398", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Boselewa", "depth": 10, "iso_1_code": null, "iso_3_code": "bwf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2399", "native_tokenizers": [], "scripts": [] }, { "name": "Dobu", "depth": 10, "iso_1_code": null, "iso_3_code": "dob", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2400", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Duau", "depth": 10, "iso_1_code": null, "iso_3_code": "dva", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2401", "native_tokenizers": [], "scripts": [] }, { "name": "Galeya", "depth": 10, "iso_1_code": null, "iso_3_code": "gar", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2402", "native_tokenizers": [], "scripts": [] }, { "name": "Mwatebu", "depth": 10, "iso_1_code": null, "iso_3_code": "mwa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2403", "native_tokenizers": [], "scripts": [] }, { "name": "Sewa Bay", "depth": 10, "iso_1_code": null, "iso_3_code": "sew", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2404", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2397", "native_tokenizers": [], "scripts": [] }, { "name": "Gumawana", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gumawana", "depth": 10, "iso_1_code": null, "iso_3_code": "gvs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2406", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2405", "native_tokenizers": [], "scripts": [] }, { "name": "Kakabai", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dawawa", "depth": 10, "iso_1_code": null, "iso_3_code": "dww", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2408", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kakabai", "depth": 10, "iso_1_code": null, "iso_3_code": "kqf", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2409", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2407", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2367", "native_tokenizers": [], "scripts": [] }, { "name": "Suauic", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buhutu", "depth": 9, "iso_1_code": null, "iso_3_code": "bxh", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2411", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "\u2019Auhelawa", "depth": 9, "iso_1_code": null, "iso_3_code": "kud", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2412", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Oya\u2019oya", "depth": 9, "iso_1_code": null, "iso_3_code": "oyy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2413", "native_tokenizers": [], "scripts": [] }, { "name": "Saliba", "depth": 9, "iso_1_code": null, "iso_3_code": "sbe", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2414", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Suau", "depth": 9, "iso_1_code": null, "iso_3_code": "swp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2415", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bwanabwana", "depth": 9, "iso_1_code": null, "iso_3_code": "tte", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2416", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Unubahe", "depth": 9, "iso_1_code": null, "iso_3_code": "unu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2417", "native_tokenizers": [], "scripts": [] }, { "name": "Wagawaga", "depth": 9, "iso_1_code": null, "iso_3_code": "wgb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2418", "native_tokenizers": [], "scripts": [] }, { "name": "Yaleba", "depth": 9, "iso_1_code": null, "iso_3_code": "ylb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2419", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2410", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2364", "native_tokenizers": [], "scripts": [] }, { "name": "Peripheral", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Papuan", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Oumic", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ouma", "depth": 10, "iso_1_code": null, "iso_3_code": "oum", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2423", "native_tokenizers": [], "scripts": [] }, { "name": "Magoric", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bina", "depth": 11, "iso_1_code": null, "iso_3_code": "bmn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2425", "native_tokenizers": [], "scripts": [] }, { "name": "Yoba", "depth": 11, "iso_1_code": null, "iso_3_code": "yob", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2426", "native_tokenizers": [], "scripts": [] }, { "name": "Magori", "depth": 11, "iso_1_code": null, "iso_3_code": "zgr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2427", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2424", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2422", "native_tokenizers": [], "scripts": [] }, { "name": "Sinagoro-Keapara", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Vula\u2019a", "depth": 10, "iso_1_code": null, "iso_3_code": "hul", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2429", "native_tokenizers": [], "scripts": [] }, { "name": "Keapara", "depth": 10, "iso_1_code": null, "iso_3_code": "khz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2430", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Motu", "depth": 10, "iso_1_code": null, "iso_3_code": "meu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2431", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sinaugoro", "depth": 10, "iso_1_code": null, "iso_3_code": "snc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2432", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2428", "native_tokenizers": [], "scripts": [] }, { "name": "West Central Papuan", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gabadi", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Abadi", "depth": 11, "iso_1_code": null, "iso_3_code": "kbt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2435", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2434", "native_tokenizers": [], "scripts": [] }, { "name": "Nuclear", "depth": 10, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Toura", "depth": 11, "iso_1_code": null, "iso_3_code": "don", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2437", "native_tokenizers": [], "scripts": [] }, { "name": "Kuni", "depth": 11, "iso_1_code": null, "iso_3_code": "kse", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2438", "native_tokenizers": [], "scripts": [] }, { "name": "Mekeo", "depth": 11, "iso_1_code": null, "iso_3_code": "mek", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2439", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lala", "depth": 11, "iso_1_code": null, "iso_3_code": "nrz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2440", "native_tokenizers": [], "scripts": [] }, { "name": "Waima", "depth": 11, "iso_1_code": null, "iso_3_code": "rro", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2441", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2436", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2433", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2421", "native_tokenizers": [], "scripts": [] }, { "name": "Kilivila-Louisiades", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kilivila", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Budibud", "depth": 10, "iso_1_code": null, "iso_3_code": "btp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2444", "native_tokenizers": [], "scripts": [] }, { "name": "Kilivila", "depth": 10, "iso_1_code": null, "iso_3_code": "kij", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2445", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Muyuw", "depth": 10, "iso_1_code": null, "iso_3_code": "myw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2446", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2443", "native_tokenizers": [], "scripts": [] }, { "name": "Misima", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Misima-Panaeati", "depth": 10, "iso_1_code": null, "iso_3_code": "mpx", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2448", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2447", "native_tokenizers": [], "scripts": [] }, { "name": "Nimoa-Sudest", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rifao", "depth": 10, "iso_1_code": null, "iso_3_code": "nmw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2450", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sudest", "depth": 10, "iso_1_code": null, "iso_3_code": "tgo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2451", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2449", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2442", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2420", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2363", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2108", "native_tokenizers": [], "scripts": [] }, { "name": "Yapese", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yapese", "depth": 6, "iso_1_code": null, "iso_3_code": "yap", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2453", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2452", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1739", "native_tokenizers": [], "scripts": [] }, { "name": "South Halmahera-West New Guinea", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "South Halmahera", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Irarutu", "depth": 6, "iso_1_code": null, "iso_3_code": "irh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2456", "native_tokenizers": [], "scripts": [] }, { "name": "East Makian-Gane", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gane", "depth": 7, "iso_1_code": null, "iso_3_code": "gzn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2458", "native_tokenizers": [], "scripts": [] }, { "name": "Makian, East", "depth": 7, "iso_1_code": null, "iso_3_code": "mky", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2459", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2457", "native_tokenizers": [], "scripts": [] }, { "name": "Southeast", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buli", "depth": 7, "iso_1_code": null, "iso_3_code": "bzq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2461", "native_tokenizers": [], "scripts": [] }, { "name": "Maba", "depth": 7, "iso_1_code": null, "iso_3_code": "mqa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2462", "native_tokenizers": [], "scripts": [] }, { "name": "Patani", "depth": 7, "iso_1_code": null, "iso_3_code": "ptn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2463", "native_tokenizers": [], "scripts": [] }, { "name": "Sawai", "depth": 7, "iso_1_code": null, "iso_3_code": "szw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2464", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2460", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2455", "native_tokenizers": [], "scripts": [] }, { "name": "West New Guinea", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bomberai", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bedoanas", "depth": 7, "iso_1_code": null, "iso_3_code": "bed", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2467", "native_tokenizers": [], "scripts": [] }, { "name": "Erokwanas", "depth": 7, "iso_1_code": null, "iso_3_code": "erw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2468", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2466", "native_tokenizers": [], "scripts": [] }, { "name": "Cenderawasih Bay", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Biakic", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Biak", "depth": 8, "iso_1_code": null, "iso_3_code": "bhw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2471", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Dusner", "depth": 8, "iso_1_code": null, "iso_3_code": "dsn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2472", "native_tokenizers": [], "scripts": [] }, { "name": "Meoswar", "depth": 8, "iso_1_code": null, "iso_3_code": "mvx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2473", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2470", "native_tokenizers": [], "scripts": [] }, { "name": "Iresim", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yeresiam", "depth": 8, "iso_1_code": null, "iso_3_code": "ire", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2475", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2474", "native_tokenizers": [], "scripts": [] }, { "name": "Mor", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mor", "depth": 8, "iso_1_code": null, "iso_3_code": "mhz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2477", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2476", "native_tokenizers": [], "scripts": [] }, { "name": "Raja Ampat", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "As", "depth": 8, "iso_1_code": null, "iso_3_code": "asz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2479", "native_tokenizers": [], "scripts": [] }, { "name": "Biga", "depth": 8, "iso_1_code": null, "iso_3_code": "bhc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2480", "native_tokenizers": [], "scripts": [] }, { "name": "Gebe", "depth": 8, "iso_1_code": null, "iso_3_code": "gei", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2481", "native_tokenizers": [], "scripts": [] }, { "name": "Kawe", "depth": 8, "iso_1_code": null, "iso_3_code": "kgb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2482", "native_tokenizers": [], "scripts": [] }, { "name": "Legenyem", "depth": 8, "iso_1_code": null, "iso_3_code": "lcc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2483", "native_tokenizers": [], "scripts": [] }, { "name": "Ma\u2019ya", "depth": 8, "iso_1_code": null, "iso_3_code": "slz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2484", "native_tokenizers": [], "scripts": [] }, { "name": "Ambel", "depth": 8, "iso_1_code": null, "iso_3_code": "wgo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2485", "native_tokenizers": [], "scripts": [] }, { "name": "Wauyai", "depth": 8, "iso_1_code": null, "iso_3_code": "wuy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2486", "native_tokenizers": [], "scripts": [] }, { "name": "Matbat", "depth": 8, "iso_1_code": null, "iso_3_code": "xmt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2487", "native_tokenizers": [], "scripts": [] }, { "name": "Salawati", "depth": 8, "iso_1_code": null, "iso_3_code": "xmx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2488", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2478", "native_tokenizers": [], "scripts": [] }, { "name": "Tandia", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tandia", "depth": 8, "iso_1_code": null, "iso_3_code": "tni", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2490", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2489", "native_tokenizers": [], "scripts": [] }, { "name": "Waropen", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Waropen", "depth": 8, "iso_1_code": null, "iso_3_code": "wrp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2492", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2491", "native_tokenizers": [], "scripts": [] }, { "name": "Yapen", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central-Western", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ambai", "depth": 9, "iso_1_code": null, "iso_3_code": "amk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2495", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ansus", "depth": 9, "iso_1_code": null, "iso_3_code": "and", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2496", "native_tokenizers": [], "scripts": [] }, { "name": "Busami", "depth": 9, "iso_1_code": null, "iso_3_code": "bsm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2497", "native_tokenizers": [], "scripts": [] }, { "name": "Munggui", "depth": 9, "iso_1_code": null, "iso_3_code": "mth", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2498", "native_tokenizers": [], "scripts": [] }, { "name": "Marau", "depth": 9, "iso_1_code": null, "iso_3_code": "mvr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2499", "native_tokenizers": [], "scripts": [] }, { "name": "Pom", "depth": 9, "iso_1_code": null, "iso_3_code": "pmo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2500", "native_tokenizers": [], "scripts": [] }, { "name": "Papuma", "depth": 9, "iso_1_code": null, "iso_3_code": "ppm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2501", "native_tokenizers": [], "scripts": [] }, { "name": "Roon", "depth": 9, "iso_1_code": null, "iso_3_code": "rnn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2502", "native_tokenizers": [], "scripts": [] }, { "name": "Serui-Laut", "depth": 9, "iso_1_code": null, "iso_3_code": "seu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2503", "native_tokenizers": [], "scripts": [] }, { "name": "Wamesa", "depth": 9, "iso_1_code": null, "iso_3_code": "wad", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2504", "native_tokenizers": [], "scripts": [] }, { "name": "Woi", "depth": 9, "iso_1_code": null, "iso_3_code": "wbw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2505", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2494", "native_tokenizers": [], "scripts": [] }, { "name": "East", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kurudu", "depth": 9, "iso_1_code": null, "iso_3_code": "kjr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2507", "native_tokenizers": [], "scripts": [] }, { "name": "Wabo", "depth": 9, "iso_1_code": null, "iso_3_code": "wbb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2508", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2506", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2493", "native_tokenizers": [], "scripts": [] }, { "name": "Yaur", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yaur", "depth": 8, "iso_1_code": null, "iso_3_code": "jau", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2510", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2509", "native_tokenizers": [], "scripts": [] }, { "name": "Yeretuar", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yeretuar", "depth": 8, "iso_1_code": null, "iso_3_code": "gop", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2512", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2511", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2469", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2465", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2454", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1738", "native_tokenizers": [], "scripts": [] }, { "name": "Hukumina", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hukumina", "depth": 4, "iso_1_code": null, "iso_3_code": "huw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2514", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2513", "native_tokenizers": [], "scripts": [] }, { "name": "North Bomberai", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arguni", "depth": 4, "iso_1_code": null, "iso_3_code": "agf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2516", "native_tokenizers": [], "scripts": [] }, { "name": "Onin", "depth": 4, "iso_1_code": null, "iso_3_code": "oni", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2517", "native_tokenizers": [], "scripts": [] }, { "name": "Sekar", "depth": 4, "iso_1_code": null, "iso_3_code": "skz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2518", "native_tokenizers": [], "scripts": [] }, { "name": "Uruangnirin", "depth": 4, "iso_1_code": null, "iso_3_code": "urn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2519", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2515", "native_tokenizers": [], "scripts": [] }, { "name": "South Bomberai", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kowiai", "depth": 4, "iso_1_code": null, "iso_3_code": "kwh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2521", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2520", "native_tokenizers": [], "scripts": [] }, { "name": "Southeast Maluku", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kei-Tanimbar", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kei-Fordata", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Fordata", "depth": 6, "iso_1_code": null, "iso_3_code": "frd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2525", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kei", "depth": 6, "iso_1_code": null, "iso_3_code": "kei", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2526", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2524", "native_tokenizers": [], "scripts": [] }, { "name": "Yamdena", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yamdena", "depth": 6, "iso_1_code": null, "iso_3_code": "jmd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2528", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2527", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2523", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Selaru", "depth": 5, "iso_1_code": null, "iso_3_code": "slu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2530", "native_tokenizers": [], "scripts": [] }, { "name": "Seluwasan", "depth": 5, "iso_1_code": null, "iso_3_code": "sws", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2531", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2529", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2522", "native_tokenizers": [], "scripts": [] }, { "name": "Sumba-Hawu", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hawu-Dhao", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hawu", "depth": 5, "iso_1_code": null, "iso_3_code": "hvn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2534", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Dhao", "depth": 5, "iso_1_code": null, "iso_3_code": "nfa", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2535", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2533", "native_tokenizers": [], "scripts": [] }, { "name": "Sumba", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Anakalangu", "depth": 5, "iso_1_code": null, "iso_3_code": "akg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2537", "native_tokenizers": [], "scripts": [] }, { "name": "Kodi", "depth": 5, "iso_1_code": null, "iso_3_code": "kod", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2538", "native_tokenizers": [], "scripts": [] }, { "name": "Lamboya", "depth": 5, "iso_1_code": null, "iso_3_code": "lmy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2539", "native_tokenizers": [], "scripts": [] }, { "name": "Loura", "depth": 5, "iso_1_code": null, "iso_3_code": "lur", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2540", "native_tokenizers": [], "scripts": [] }, { "name": "Mamboru", "depth": 5, "iso_1_code": null, "iso_3_code": "mvd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2541", "native_tokenizers": [], "scripts": [] }, { "name": "Wejewa", "depth": 5, "iso_1_code": null, "iso_3_code": "wew", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2542", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Wanukaka", "depth": 5, "iso_1_code": null, "iso_3_code": "wnk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2543", "native_tokenizers": [], "scripts": [] }, { "name": "Kambera", "depth": 5, "iso_1_code": null, "iso_3_code": "xbr", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2544", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2536", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2532", "native_tokenizers": [], "scripts": [] }, { "name": "Teor-Kur", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kur", "depth": 4, "iso_1_code": null, "iso_3_code": "kuv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2546", "native_tokenizers": [], "scripts": [] }, { "name": "Teor", "depth": 4, "iso_1_code": null, "iso_3_code": "tev", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2547", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2545", "native_tokenizers": [], "scripts": [] }, { "name": "Timor-Babar", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nuclear Timor", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Galolen", "depth": 5, "iso_1_code": null, "iso_3_code": "gal", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2550", "native_tokenizers": [], "scripts": [] }, { "name": "Habun", "depth": 5, "iso_1_code": null, "iso_3_code": "hbu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2551", "native_tokenizers": [], "scripts": [] }, { "name": "Helong", "depth": 5, "iso_1_code": null, "iso_3_code": "heg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2552", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Idat\u00e9", "depth": 5, "iso_1_code": null, "iso_3_code": "idt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2553", "native_tokenizers": [], "scripts": [] }, { "name": "Kemak", "depth": 5, "iso_1_code": null, "iso_3_code": "kem", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2554", "native_tokenizers": [], "scripts": [] }, { "name": "Kairui-Midiki", "depth": 5, "iso_1_code": null, "iso_3_code": "krd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2555", "native_tokenizers": [], "scripts": [] }, { "name": "Lakalei", "depth": 5, "iso_1_code": null, "iso_3_code": "lka", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2556", "native_tokenizers": [], "scripts": [] }, { "name": "Makuva", "depth": 5, "iso_1_code": null, "iso_3_code": "lva", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2557", "native_tokenizers": [], "scripts": [] }, { "name": "Mambae", "depth": 5, "iso_1_code": null, "iso_3_code": "mgm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2558", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Nauete", "depth": 5, "iso_1_code": null, "iso_3_code": "nxa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2559", "native_tokenizers": [], "scripts": [] }, { "name": "Tetun", "depth": 5, "iso_1_code": null, "iso_3_code": "tet", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2560", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tukudede", "depth": 5, "iso_1_code": null, "iso_3_code": "tkd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2561", "native_tokenizers": [], "scripts": [] }, { "name": "Welaun", "depth": 5, "iso_1_code": null, "iso_3_code": "wlh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2562", "native_tokenizers": [], "scripts": [] }, { "name": "Waima\u2019a", "depth": 5, "iso_1_code": null, "iso_3_code": "wmh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2563", "native_tokenizers": [], "scripts": [] }, { "name": "Rote", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bilba", "depth": 6, "iso_1_code": null, "iso_3_code": "bpz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2565", "native_tokenizers": [], "scripts": [] }, { "name": "Dengka", "depth": 6, "iso_1_code": null, "iso_3_code": "dnk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2566", "native_tokenizers": [], "scripts": [] }, { "name": "Lole", "depth": 6, "iso_1_code": null, "iso_3_code": "llg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2567", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Rikou", "depth": 6, "iso_1_code": null, "iso_3_code": "rgu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2568", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Dela-Oenale", "depth": 6, "iso_1_code": null, "iso_3_code": "row", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2569", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Termanu", "depth": 6, "iso_1_code": null, "iso_3_code": "twu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2570", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tii", "depth": 6, "iso_1_code": null, "iso_3_code": "txq", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2571", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2564", "native_tokenizers": [], "scripts": [] }, { "name": "Uab Meto", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Amarasi", "depth": 6, "iso_1_code": null, "iso_3_code": "aaz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2573", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Uab Meto", "depth": 6, "iso_1_code": null, "iso_3_code": "aoz", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2574", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Baikeno", "depth": 6, "iso_1_code": null, "iso_3_code": "bkx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2575", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2572", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2549", "native_tokenizers": [], "scripts": [] }, { "name": "Southwest Maluku", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East Damar", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Damar, East", "depth": 6, "iso_1_code": null, "iso_3_code": "dmr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2578", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2577", "native_tokenizers": [], "scripts": [] }, { "name": "Kisar-Roma", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kisar", "depth": 6, "iso_1_code": null, "iso_3_code": "kje", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2580", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Roma", "depth": 6, "iso_1_code": null, "iso_3_code": "rmm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2581", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2579", "native_tokenizers": [], "scripts": [] }, { "name": "Luang", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Luang", "depth": 6, "iso_1_code": null, "iso_3_code": "lex", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2583", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Leti", "depth": 6, "iso_1_code": null, "iso_3_code": "lti", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2584", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2582", "native_tokenizers": [], "scripts": [] }, { "name": "Teun-Nila-Serua", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nila-Serua", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nila", "depth": 7, "iso_1_code": null, "iso_3_code": "nil", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2587", "native_tokenizers": [], "scripts": [] }, { "name": "Serua", "depth": 7, "iso_1_code": null, "iso_3_code": "srw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2588", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2586", "native_tokenizers": [], "scripts": [] }, { "name": "Teun", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Te\u2019un", "depth": 7, "iso_1_code": null, "iso_3_code": "tve", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2590", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2589", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2585", "native_tokenizers": [], "scripts": [] }, { "name": "Wetar", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Atauran", "depth": 6, "iso_1_code": null, "iso_3_code": "adb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2592", "native_tokenizers": [], "scripts": [] }, { "name": "Aputai", "depth": 6, "iso_1_code": null, "iso_3_code": "apx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2593", "native_tokenizers": [], "scripts": [] }, { "name": "Ili\u2019uun", "depth": 6, "iso_1_code": null, "iso_3_code": "ilu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2594", "native_tokenizers": [], "scripts": [] }, { "name": "Tugun", "depth": 6, "iso_1_code": null, "iso_3_code": "tzn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2595", "native_tokenizers": [], "scripts": [] }, { "name": "Perai", "depth": 6, "iso_1_code": null, "iso_3_code": "wet", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2596", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2591", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2576", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2548", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kuri", "depth": 4, "iso_1_code": null, "iso_3_code": "nbn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2598", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2597", "native_tokenizers": [], "scripts": [] }, { "name": "West Damar", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Damar, West", "depth": 4, "iso_1_code": null, "iso_3_code": "drn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2600", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2599", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1589", "native_tokenizers": [], "scripts": [] }, { "name": "Chamorro", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chamorro", "depth": 3, "iso_1_code": "ch", "iso_3_code": "cha", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2602", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2601", "native_tokenizers": [], "scripts": [] }, { "name": "Greater Barito", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Barito-Mahakam", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ampanang", "depth": 4, "iso_1_code": null, "iso_3_code": "apg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2605", "native_tokenizers": [], "scripts": [] }, { "name": "Tunjung", "depth": 4, "iso_1_code": null, "iso_3_code": "tjg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2606", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2604", "native_tokenizers": [], "scripts": [] }, { "name": "East", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central-South", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dusun Deyah", "depth": 6, "iso_1_code": null, "iso_3_code": "dun", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2610", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2609", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dusun Malang", "depth": 6, "iso_1_code": null, "iso_3_code": "duq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2612", "native_tokenizers": [], "scripts": [] }, { "name": "Dusun Witu", "depth": 6, "iso_1_code": null, "iso_3_code": "duw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2613", "native_tokenizers": [], "scripts": [] }, { "name": "Ma\u2019anyan", "depth": 6, "iso_1_code": null, "iso_3_code": "mhy", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2614", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Paku", "depth": 6, "iso_1_code": null, "iso_3_code": "pku", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2615", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2611", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2608", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Malagasy, Bara", "depth": 5, "iso_1_code": "mg", "iso_3_code": "bhr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2617", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy, Northern Betsimisaraka", "depth": 5, "iso_1_code": "mg", "iso_3_code": "bmm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2618", "native_tokenizers": [], "scripts": [] }, { "name": "Bushi", "depth": 5, "iso_1_code": null, "iso_3_code": "buc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2619", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy, Southern Betsimisaraka", "depth": 5, "iso_1_code": "mg", "iso_3_code": "bzc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2620", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy, Masikoro", "depth": 5, "iso_1_code": "mg", "iso_3_code": "msh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2621", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy, Merina", "depth": 5, "iso_1_code": "mg", "iso_3_code": "plt", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2622", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Malagasy, Sakalava", "depth": 5, "iso_1_code": "mg", "iso_3_code": "skg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2623", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Malagasy, Tandroy-Mahafaly", "depth": 5, "iso_1_code": "mg", "iso_3_code": "tdx", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2624", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Malagasy, Tesaka", "depth": 5, "iso_1_code": "mg", "iso_3_code": "tkg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2625", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy, Tanosy", "depth": 5, "iso_1_code": "mg", "iso_3_code": "txy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2626", "native_tokenizers": [], "scripts": [] }, { "name": "Malagasy, Antankarana", "depth": 5, "iso_1_code": "mg", "iso_3_code": "xmv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2627", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Malagasy, Tsimihety", "depth": 5, "iso_1_code": "mg", "iso_3_code": "xmw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2628", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2616", "native_tokenizers": [], "scripts": [] }, { "name": "North", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lawangan", "depth": 5, "iso_1_code": null, "iso_3_code": "lbx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2630", "native_tokenizers": [], "scripts": [] }, { "name": "Tawoyan", "depth": 5, "iso_1_code": null, "iso_3_code": "twy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2631", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2629", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2607", "native_tokenizers": [], "scripts": [] }, { "name": "Sama-Bajaw", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yakan", "depth": 4, "iso_1_code": null, "iso_3_code": "yka", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2633", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Abaknon", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Inabaknon", "depth": 5, "iso_1_code": null, "iso_3_code": "abx", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2635", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2634", "native_tokenizers": [], "scripts": [] }, { "name": "Sulu-Borneo", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Borneo Coast Bajaw", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bajau, Indonesian", "depth": 6, "iso_1_code": null, "iso_3_code": "bdl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2638", "native_tokenizers": [], "scripts": [] }, { "name": "Bajau, West Coast", "depth": 6, "iso_1_code": null, "iso_3_code": "bdr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2639", "native_tokenizers": [], "scripts": [] }, { "name": "Mapun", "depth": 6, "iso_1_code": null, "iso_3_code": "sjm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2640", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2637", "native_tokenizers": [], "scripts": [] }, { "name": "Inner Sulu Sama", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sama, Central", "depth": 6, "iso_1_code": null, "iso_3_code": "sml", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2642", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sama, Southern", "depth": 6, "iso_1_code": null, "iso_3_code": "ssb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2643", "native_tokenizers": [], "scripts": [] }, { "name": "Sama, Balangingih", "depth": 6, "iso_1_code": null, "iso_3_code": "sse", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2644", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2641", "native_tokenizers": [], "scripts": [] }, { "name": "Western Sulu Sama", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sama, Pangutaran", "depth": 6, "iso_1_code": null, "iso_3_code": "slm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2646", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2645", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2636", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2632", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kohin", "depth": 5, "iso_1_code": null, "iso_3_code": "kkx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2649", "native_tokenizers": [], "scripts": [] }, { "name": "Ot Danum", "depth": 5, "iso_1_code": null, "iso_3_code": "otd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2650", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Siang", "depth": 5, "iso_1_code": null, "iso_3_code": "sya", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2651", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2648", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bakumpai", "depth": 5, "iso_1_code": null, "iso_3_code": "bkr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2653", "native_tokenizers": [], "scripts": [] }, { "name": "Ngaju", "depth": 5, "iso_1_code": null, "iso_3_code": "nij", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2654", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2652", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2647", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2603", "native_tokenizers": [], "scripts": [] }, { "name": "Greater Central Philippine", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Philippine", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ata", "depth": 4, "iso_1_code": null, "iso_3_code": "atm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2657", "native_tokenizers": [], "scripts": [] }, { "name": "Ayta, Sorsogon", "depth": 4, "iso_1_code": null, "iso_3_code": "ays", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2658", "native_tokenizers": [], "scripts": [] }, { "name": "Binukidnon, Northern", "depth": 4, "iso_1_code": null, "iso_3_code": "kyn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2659", "native_tokenizers": [], "scripts": [] }, { "name": "Binukidnon, Southern", "depth": 4, "iso_1_code": null, "iso_3_code": "mtw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2660", "native_tokenizers": [], "scripts": [] }, { "name": "Sulod", "depth": 4, "iso_1_code": null, "iso_3_code": "srg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2661", "native_tokenizers": [], "scripts": [] }, { "name": "Bikol", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Coastal", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Naga", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agta, Katubung", "depth": 7, "iso_1_code": null, "iso_3_code": "agk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2665", "native_tokenizers": [], "scripts": [] }, { "name": "Agta, Mt. Iraya", "depth": 7, "iso_1_code": null, "iso_3_code": "atl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2666", "native_tokenizers": [], "scripts": [] }, { "name": "Bikol, Central", "depth": 7, "iso_1_code": null, "iso_3_code": "bcl", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2667", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2664", "native_tokenizers": [], "scripts": [] }, { "name": "Virac", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bikol, Southern Catanduanes", "depth": 7, "iso_1_code": null, "iso_3_code": "bln", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2669", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2668", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2663", "native_tokenizers": [], "scripts": [] }, { "name": "Inland", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agta, Mt. Iriga", "depth": 6, "iso_1_code": null, "iso_3_code": "agz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2671", "native_tokenizers": [], "scripts": [] }, { "name": "Bikol, West Albay", "depth": 6, "iso_1_code": null, "iso_3_code": "fbl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2672", "native_tokenizers": [], "scripts": [] }, { "name": "Bikol, Libon", "depth": 6, "iso_1_code": null, "iso_3_code": "lbl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2673", "native_tokenizers": [], "scripts": [] }, { "name": "Bikol, Miraya", "depth": 6, "iso_1_code": null, "iso_3_code": "rbl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2674", "native_tokenizers": [], "scripts": [] }, { "name": "Bikol, Buhi\u2019non", "depth": 6, "iso_1_code": null, "iso_3_code": "ubl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2675", "native_tokenizers": [], "scripts": [] }, { "name": "Iriga", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bikol, Rinconada", "depth": 7, "iso_1_code": null, "iso_3_code": "bto", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2677", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2676", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2670", "native_tokenizers": [], "scripts": [] }, { "name": "Pandan", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bikol, Northern Catanduanes", "depth": 6, "iso_1_code": null, "iso_3_code": "cts", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2679", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2678", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2662", "native_tokenizers": [], "scripts": [] }, { "name": "Bisayan", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Banton", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bantoanon", "depth": 6, "iso_1_code": null, "iso_3_code": "bno", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2682", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2681", "native_tokenizers": [], "scripts": [] }, { "name": "Cebuan", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cebuano", "depth": 6, "iso_1_code": null, "iso_3_code": "ceb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2684", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2683", "native_tokenizers": [], "scripts": [] }, { "name": "Central", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bantayanon", "depth": 6, "iso_1_code": null, "iso_3_code": "bfx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2686", "native_tokenizers": [], "scripts": [] }, { "name": "Peripheral", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ati", "depth": 7, "iso_1_code": null, "iso_3_code": "atk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2688", "native_tokenizers": [], "scripts": [] }, { "name": "Capiznon", "depth": 7, "iso_1_code": null, "iso_3_code": "cps", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2689", "native_tokenizers": [], "scripts": [] }, { "name": "Hiligaynon", "depth": 7, "iso_1_code": null, "iso_3_code": "hil", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2690", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Masbatenyo", "depth": 7, "iso_1_code": null, "iso_3_code": "msb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2691", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Porohanon", "depth": 7, "iso_1_code": null, "iso_3_code": "prh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2692", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2687", "native_tokenizers": [], "scripts": [] }, { "name": "Romblon", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Romblomanon", "depth": 7, "iso_1_code": null, "iso_3_code": "rol", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2694", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2693", "native_tokenizers": [], "scripts": [] }, { "name": "Warayan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sorsoganon, Northern", "depth": 7, "iso_1_code": null, "iso_3_code": "bks", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2696", "native_tokenizers": [], "scripts": [] }, { "name": "Baybayanon", "depth": 7, "iso_1_code": null, "iso_3_code": "bvy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2697", "native_tokenizers": [], "scripts": [] }, { "name": "Kinabalian", "depth": 7, "iso_1_code": null, "iso_3_code": "cbw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2698", "native_tokenizers": [], "scripts": [] }, { "name": "Gubat", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sorsoganon, Southern", "depth": 8, "iso_1_code": null, "iso_3_code": "srv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2700", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2699", "native_tokenizers": [], "scripts": [] }, { "name": "Samar-Waray", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Waray-Waray", "depth": 8, "iso_1_code": null, "iso_3_code": "war", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2702", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2701", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2695", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2685", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Surigaonon", "depth": 6, "iso_1_code": null, "iso_3_code": "sgd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2704", "native_tokenizers": [], "scripts": [] }, { "name": "Tandaganon", "depth": 6, "iso_1_code": null, "iso_3_code": "tgn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2705", "native_tokenizers": [], "scripts": [] }, { "name": "Butuan-Tausug", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Butuanon", "depth": 7, "iso_1_code": null, "iso_3_code": "btw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2707", "native_tokenizers": [], "scripts": [] }, { "name": "Tausug", "depth": 7, "iso_1_code": null, "iso_3_code": "tsg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2708", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2706", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2703", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Caluyanun", "depth": 6, "iso_1_code": null, "iso_3_code": "clu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2710", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Aklan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aklanon", "depth": 7, "iso_1_code": null, "iso_3_code": "akl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2712", "native_tokenizers": [], "scripts": [] }, { "name": "Malaynon", "depth": 7, "iso_1_code": null, "iso_3_code": "mlz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2713", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2711", "native_tokenizers": [], "scripts": [] }, { "name": "Kinarayan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kinaray-a", "depth": 7, "iso_1_code": null, "iso_3_code": "krj", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2715", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2714", "native_tokenizers": [], "scripts": [] }, { "name": "Kuyan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ratagnon", "depth": 7, "iso_1_code": null, "iso_3_code": "btn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2717", "native_tokenizers": [], "scripts": [] }, { "name": "Cuyonon", "depth": 7, "iso_1_code": null, "iso_3_code": "cyo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2718", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2716", "native_tokenizers": [], "scripts": [] }, { "name": "North Central", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Inonhan", "depth": 7, "iso_1_code": null, "iso_3_code": "loc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2720", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2719", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2709", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2680", "native_tokenizers": [], "scripts": [] }, { "name": "Mamanwa", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Minamanwa", "depth": 5, "iso_1_code": null, "iso_3_code": "mmn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2722", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2721", "native_tokenizers": [], "scripts": [] }, { "name": "Mansakan", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Davawenyo", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Davawenyo", "depth": 6, "iso_1_code": null, "iso_3_code": "daw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2725", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2724", "native_tokenizers": [], "scripts": [] }, { "name": "Eastern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mandaya", "depth": 6, "iso_1_code": null, "iso_3_code": "mry", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2727", "native_tokenizers": [], "scripts": [] }, { "name": "Mansaka", "depth": 6, "iso_1_code": null, "iso_3_code": "msk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2728", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2726", "native_tokenizers": [], "scripts": [] }, { "name": "Northern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kamayo", "depth": 6, "iso_1_code": null, "iso_3_code": "kyk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2730", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2729", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tagakolu", "depth": 6, "iso_1_code": null, "iso_3_code": "klg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2732", "native_tokenizers": [], "scripts": [] }, { "name": "Kalagan, Kagan", "depth": 6, "iso_1_code": null, "iso_3_code": "kll", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2733", "native_tokenizers": [], "scripts": [] }, { "name": "Kalagan", "depth": 6, "iso_1_code": null, "iso_3_code": "kqe", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2734", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2731", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2723", "native_tokenizers": [], "scripts": [] }, { "name": "Tagalog", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Filipino", "depth": 5, "iso_1_code": null, "iso_3_code": "fil", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2736", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn" ] }, { "name": "Tagalog", "depth": 5, "iso_1_code": "tl", "iso_3_code": "tgl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2737", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2735", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2656", "native_tokenizers": [], "scripts": [] }, { "name": "Danao", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Magindanao", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Maguindanaon", "depth": 5, "iso_1_code": null, "iso_3_code": "mdh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2740", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2739", "native_tokenizers": [], "scripts": [] }, { "name": "Maranao-Iranon", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Iranun", "depth": 5, "iso_1_code": null, "iso_3_code": "ilm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2742", "native_tokenizers": [], "scripts": [] }, { "name": "Iranun", "depth": 5, "iso_1_code": null, "iso_3_code": "ilp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2743", "native_tokenizers": [], "scripts": [] }, { "name": "Maranao", "depth": 5, "iso_1_code": null, "iso_3_code": "mrw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2744", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2741", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2738", "native_tokenizers": [], "scripts": [] }, { "name": "Gorontalo-Mongondow", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gorontalic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bolango", "depth": 5, "iso_1_code": null, "iso_3_code": "bld", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2747", "native_tokenizers": [], "scripts": [] }, { "name": "Buol", "depth": 5, "iso_1_code": null, "iso_3_code": "blf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2748", "native_tokenizers": [], "scripts": [] }, { "name": "Bintauna", "depth": 5, "iso_1_code": null, "iso_3_code": "bne", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2749", "native_tokenizers": [], "scripts": [] }, { "name": "Gorontalo", "depth": 5, "iso_1_code": null, "iso_3_code": "gor", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2750", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kaidipang", "depth": 5, "iso_1_code": null, "iso_3_code": "kzp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2751", "native_tokenizers": [], "scripts": [] }, { "name": "Lolak", "depth": 5, "iso_1_code": null, "iso_3_code": "llq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2752", "native_tokenizers": [], "scripts": [] }, { "name": "Suwawa", "depth": 5, "iso_1_code": null, "iso_3_code": "swu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2753", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2746", "native_tokenizers": [], "scripts": [] }, { "name": "Mongondowic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mongondow", "depth": 5, "iso_1_code": null, "iso_3_code": "mog", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2755", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ponosakan", "depth": 5, "iso_1_code": null, "iso_3_code": "pns", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2756", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2754", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2745", "native_tokenizers": [], "scripts": [] }, { "name": "Manobo", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manobo, Dibabawon", "depth": 6, "iso_1_code": null, "iso_3_code": "mbd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2760", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Manobo, Rajah Kabunsuwan", "depth": 6, "iso_1_code": null, "iso_3_code": "mqk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2761", "native_tokenizers": [], "scripts": [] }, { "name": "Manobo, Agusan", "depth": 6, "iso_1_code": null, "iso_3_code": "msm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2762", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2759", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ata-Tigwa", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manobo, Ata", "depth": 7, "iso_1_code": null, "iso_3_code": "atd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2765", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Manobo, Matigsalug", "depth": 7, "iso_1_code": null, "iso_3_code": "mbt", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2766", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2764", "native_tokenizers": [], "scripts": [] }, { "name": "Obo", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manobo, Obo", "depth": 7, "iso_1_code": null, "iso_3_code": "obo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2768", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2767", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2763", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manobo, Western Bukidnon", "depth": 6, "iso_1_code": null, "iso_3_code": "mbb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2770", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Manobo, Ilianen", "depth": 6, "iso_1_code": null, "iso_3_code": "mbi", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2771", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2769", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2758", "native_tokenizers": [], "scripts": [] }, { "name": "North", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Binukid", "depth": 5, "iso_1_code": null, "iso_3_code": "bkd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2773", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kagayanen", "depth": 5, "iso_1_code": null, "iso_3_code": "cgc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2774", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Higaonon", "depth": 5, "iso_1_code": null, "iso_3_code": "mba", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2775", "native_tokenizers": [], "scripts": [] }, { "name": "Manobo, Kinamiging", "depth": 5, "iso_1_code": null, "iso_3_code": "mkx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2776", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2772", "native_tokenizers": [], "scripts": [] }, { "name": "South", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tagabawa", "depth": 5, "iso_1_code": null, "iso_3_code": "bgs", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2778", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Manobo, Sarangani", "depth": 5, "iso_1_code": null, "iso_3_code": "mbs", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2779", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Manobo, Cotabato", "depth": 5, "iso_1_code": null, "iso_3_code": "mta", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2780", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2777", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2757", "native_tokenizers": [], "scripts": [] }, { "name": "Palawanic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bonggi", "depth": 4, "iso_1_code": null, "iso_3_code": "bdg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2782", "native_tokenizers": [], "scripts": [] }, { "name": "Batak", "depth": 4, "iso_1_code": null, "iso_3_code": "bya", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2783", "native_tokenizers": [], "scripts": [] }, { "name": "Palawano, Central", "depth": 4, "iso_1_code": null, "iso_3_code": "plc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2784", "native_tokenizers": [], "scripts": [] }, { "name": "Palawano, Southwest", "depth": 4, "iso_1_code": null, "iso_3_code": "plv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2785", "native_tokenizers": [], "scripts": [] }, { "name": "Palawano, Brooke\u2019s Point", "depth": 4, "iso_1_code": null, "iso_3_code": "plw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2786", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Molbog", "depth": 4, "iso_1_code": null, "iso_3_code": "pwm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2787", "native_tokenizers": [], "scripts": [] }, { "name": "Tagbanwa", "depth": 4, "iso_1_code": null, "iso_3_code": "tbw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2788", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tagbanwa, Central", "depth": 4, "iso_1_code": null, "iso_3_code": "tgt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2789", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2781", "native_tokenizers": [], "scripts": [] }, { "name": "South Mangyan", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buhid-Taubuid", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buhid", "depth": 5, "iso_1_code": null, "iso_3_code": "bku", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2792", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bangon", "depth": 5, "iso_1_code": null, "iso_3_code": "bnj", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2793", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tawbuid", "depth": 5, "iso_1_code": null, "iso_3_code": "twb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2794", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2791", "native_tokenizers": [], "scripts": [] }, { "name": "Hanunoo", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hanunoo", "depth": 5, "iso_1_code": null, "iso_3_code": "hnn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2796", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2795", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2790", "native_tokenizers": [], "scripts": [] }, { "name": "Subanon", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Subanon, Western", "depth": 4, "iso_1_code": null, "iso_3_code": "suc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2798", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Eastern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Subanen, Southern", "depth": 5, "iso_1_code": null, "iso_3_code": "laa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2800", "native_tokenizers": [], "scripts": [] }, { "name": "Subanen, Eastern", "depth": 5, "iso_1_code": null, "iso_3_code": "sfe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2801", "native_tokenizers": [], "scripts": [] }, { "name": "Subanon, Kolibugan", "depth": 5, "iso_1_code": null, "iso_3_code": "skn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2802", "native_tokenizers": [], "scripts": [] }, { "name": "Subanen, Northern", "depth": 5, "iso_1_code": null, "iso_3_code": "stb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2803", "native_tokenizers": [], "scripts": [] }, { "name": "Subanen, Central", "depth": 5, "iso_1_code": null, "iso_3_code": "syb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2804", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2799", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2797", "native_tokenizers": [], "scripts": [] }, { "name": "Umiray Dumaget", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Manide", "depth": 4, "iso_1_code": null, "iso_3_code": "abd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2806", "native_tokenizers": [], "scripts": [] }, { "name": "Agta, Umiray Dumaget", "depth": 4, "iso_1_code": null, "iso_3_code": "due", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2807", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Inagta Alabat", "depth": 4, "iso_1_code": null, "iso_3_code": "dul", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2808", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2805", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"tl\")", "original_lang_name": "filipino", "original_lang_code": "fil", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2655", "native_tokenizers": [], "scripts": [] }, { "name": "Javanese", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Javanese, New Caledonian", "depth": 3, "iso_1_code": null, "iso_3_code": "jas", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2810", "native_tokenizers": [], "scripts": [] }, { "name": "Javanese", "depth": 3, "iso_1_code": "jv", "iso_3_code": "jav", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2811", "native_tokenizers": [], "scripts": [ "Latn", "Java" ] }, { "name": "Javanese, Suriname", "depth": 3, "iso_1_code": null, "iso_3_code": "jvn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2812", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Osing", "depth": 3, "iso_1_code": null, "iso_3_code": "osi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2813", "native_tokenizers": [], "scripts": [] }, { "name": "Tengger", "depth": 3, "iso_1_code": null, "iso_3_code": "tes", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2814", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2809", "native_tokenizers": [], "scripts": [] }, { "name": "Kalamian", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agutaynen", "depth": 3, "iso_1_code": null, "iso_3_code": "agn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2816", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tagbanwa, Calamian", "depth": 3, "iso_1_code": null, "iso_3_code": "tbk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2817", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2815", "native_tokenizers": [], "scripts": [] }, { "name": "Lampung", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lampung Nyo", "depth": 3, "iso_1_code": null, "iso_3_code": "abl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2819", "native_tokenizers": [], "scripts": [] }, { "name": "Komering", "depth": 3, "iso_1_code": null, "iso_3_code": "kge", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2820", "native_tokenizers": [], "scripts": [] }, { "name": "Lampung Api", "depth": 3, "iso_1_code": null, "iso_3_code": "ljp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2821", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2818", "native_tokenizers": [], "scripts": [] }, { "name": "Land Dayak", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Benyadu\u2019", "depth": 3, "iso_1_code": null, "iso_3_code": "byd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2823", "native_tokenizers": [], "scripts": [] }, { "name": "Sanggau", "depth": 3, "iso_1_code": null, "iso_3_code": "scg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2824", "native_tokenizers": [], "scripts": [] }, { "name": "Bakati\u2019", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bakati\u2019", "depth": 4, "iso_1_code": null, "iso_3_code": "bei", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2826", "native_tokenizers": [], "scripts": [] }, { "name": "Bakati\u2019, Rara", "depth": 4, "iso_1_code": null, "iso_3_code": "lra", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2827", "native_tokenizers": [], "scripts": [] }, { "name": "Bakati\u2019, Sara", "depth": 4, "iso_1_code": null, "iso_3_code": "sre", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2828", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2825", "native_tokenizers": [], "scripts": [] }, { "name": "Bidayuh", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Core", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bidayuh, Biatah", "depth": 6, "iso_1_code": null, "iso_3_code": "bth", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2832", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2831", "native_tokenizers": [], "scripts": [] }, { "name": "Sembaan", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bidayuh, Tringgus-Sembaan", "depth": 6, "iso_1_code": null, "iso_3_code": "trx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2834", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2833", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bidayuh, Bau", "depth": 6, "iso_1_code": null, "iso_3_code": "sne", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2836", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2835", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2830", "native_tokenizers": [], "scripts": [] }, { "name": "Eastern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bidayuh Serian", "depth": 5, "iso_1_code": null, "iso_3_code": "sdo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2838", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2837", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2829", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jangkang", "depth": 4, "iso_1_code": null, "iso_3_code": "djo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2840", "native_tokenizers": [], "scripts": [] }, { "name": "Beginci", "depth": 4, "iso_1_code": null, "iso_3_code": "ebc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2841", "native_tokenizers": [], "scripts": [] }, { "name": "Gerai", "depth": 4, "iso_1_code": null, "iso_3_code": "gef", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2842", "native_tokenizers": [], "scripts": [] }, { "name": "Ribun", "depth": 4, "iso_1_code": null, "iso_3_code": "rir", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2843", "native_tokenizers": [], "scripts": [] }, { "name": "Semandang", "depth": 4, "iso_1_code": null, "iso_3_code": "sdq", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2844", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Mateq", "depth": 4, "iso_1_code": null, "iso_3_code": "xem", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2845", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2839", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2822", "native_tokenizers": [], "scripts": [] }, { "name": "Madurese", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kangean", "depth": 3, "iso_1_code": null, "iso_3_code": "kkv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2847", "native_tokenizers": [], "scripts": [] }, { "name": "Madura", "depth": 3, "iso_1_code": null, "iso_3_code": "mad", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2848", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2846", "native_tokenizers": [], "scripts": [] }, { "name": "Malayo-Chamic", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chamic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Acehnese", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aceh", "depth": 5, "iso_1_code": null, "iso_3_code": "ace", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2852", "native_tokenizers": [], "scripts": [ "Arab", "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2851", "native_tokenizers": [], "scripts": [] }, { "name": "Coastal", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Haroi", "depth": 5, "iso_1_code": null, "iso_3_code": "hro", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2854", "native_tokenizers": [], "scripts": [] }, { "name": "Cham", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cham, Western", "depth": 6, "iso_1_code": null, "iso_3_code": "cja", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2856", "native_tokenizers": [], "scripts": [] }, { "name": "Cham, Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": "cjm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2857", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2855", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2853", "native_tokenizers": [], "scripts": [] }, { "name": "Highlands", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bih", "depth": 5, "iso_1_code": null, "iso_3_code": "ibh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2859", "native_tokenizers": [], "scripts": [] }, { "name": "Jarai", "depth": 5, "iso_1_code": null, "iso_3_code": "jra", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2860", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Rade", "depth": 5, "iso_1_code": null, "iso_3_code": "rad", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2861", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Chru-Northern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chru", "depth": 6, "iso_1_code": null, "iso_3_code": "cje", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2863", "native_tokenizers": [], "scripts": [] }, { "name": "Northern Cham", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tsat", "depth": 7, "iso_1_code": null, "iso_3_code": "huq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2865", "native_tokenizers": [], "scripts": [] }, { "name": "Roglai, Southern", "depth": 7, "iso_1_code": null, "iso_3_code": "rgs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2866", "native_tokenizers": [], "scripts": [] }, { "name": "Roglai, Cacgia", "depth": 7, "iso_1_code": null, "iso_3_code": "roc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2867", "native_tokenizers": [], "scripts": [] }, { "name": "Roglai, Northern", "depth": 7, "iso_1_code": null, "iso_3_code": "rog", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2868", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2864", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2862", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2858", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2850", "native_tokenizers": [], "scripts": [] }, { "name": "Malayic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Keninjal", "depth": 4, "iso_1_code": null, "iso_3_code": "knl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2870", "native_tokenizers": [], "scripts": [] }, { "name": "Kendayan", "depth": 4, "iso_1_code": null, "iso_3_code": "knx", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2871", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Urak Lawoi\u2019", "depth": 4, "iso_1_code": "ms", "iso_3_code": "urk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2872", "native_tokenizers": [], "scripts": [ "Thai" ] }, { "name": "Malayic Dayak", "depth": 4, "iso_1_code": null, "iso_3_code": "xdy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2873", "native_tokenizers": [], "scripts": [] }, { "name": "Ibanic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Iban", "depth": 5, "iso_1_code": null, "iso_3_code": "iba", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2875", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Remun", "depth": 5, "iso_1_code": null, "iso_3_code": "lkj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2876", "native_tokenizers": [], "scripts": [] }, { "name": "Mualang", "depth": 5, "iso_1_code": null, "iso_3_code": "mtd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2877", "native_tokenizers": [], "scripts": [] }, { "name": "Seberuang", "depth": 5, "iso_1_code": null, "iso_3_code": "sbx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2878", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2874", "native_tokenizers": [], "scripts": [] }, { "name": "Malay", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Banjar", "depth": 5, "iso_1_code": "ms", "iso_3_code": "bjn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2880", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn", "Arab" ] }, { "name": "Malay, Bacanese", "depth": 5, "iso_1_code": "ms", "iso_3_code": "btj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2881", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Berau", "depth": 5, "iso_1_code": "ms", "iso_3_code": "bve", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2882", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Bukit", "depth": 5, "iso_1_code": "ms", "iso_3_code": "bvu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2883", "native_tokenizers": [], "scripts": [] }, { "name": "Duano", "depth": 5, "iso_1_code": "ms", "iso_3_code": "dup", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2884", "native_tokenizers": [], "scripts": [] }, { "name": "Haji", "depth": 5, "iso_1_code": "ms", "iso_3_code": "hji", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2885", "native_tokenizers": [], "scripts": [] }, { "name": "Indonesian", "depth": 5, "iso_1_code": "id", "iso_3_code": "ind", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"id\")", "original_lang_name": "indonesian", "original_lang_code": "ind", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2886", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn" ] }, { "name": "Jakun", "depth": 5, "iso_1_code": "ms", "iso_3_code": "jak", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2887", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Jambi", "depth": 5, "iso_1_code": "ms", "iso_3_code": "jax", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2888", "native_tokenizers": [], "scripts": [] }, { "name": "Kubu", "depth": 5, "iso_1_code": "ms", "iso_3_code": "kvb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2889", "native_tokenizers": [], "scripts": [] }, { "name": "Kerinci", "depth": 5, "iso_1_code": "ms", "iso_3_code": "kvr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2890", "native_tokenizers": [], "scripts": [] }, { "name": "Brunei", "depth": 5, "iso_1_code": "ms", "iso_3_code": "kxd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2891", "native_tokenizers": [], "scripts": [] }, { "name": "Sekak", "depth": 5, "iso_1_code": "ms", "iso_3_code": "lce", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2892", "native_tokenizers": [], "scripts": [] }, { "name": "Lubu", "depth": 5, "iso_1_code": "ms", "iso_3_code": "lcf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2893", "native_tokenizers": [], "scripts": [] }, { "name": "Col", "depth": 5, "iso_1_code": "ms", "iso_3_code": "liw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2894", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Kedah", "depth": 5, "iso_1_code": "ms", "iso_3_code": "meo", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2895", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Pattani", "depth": 5, "iso_1_code": "ms", "iso_3_code": "mfa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2896", "native_tokenizers": [], "scripts": [] }, { "name": "Bangka", "depth": 5, "iso_1_code": "ms", "iso_3_code": "mfb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2897", "native_tokenizers": [], "scripts": [] }, { "name": "Indonesian, Makassar", "depth": 5, "iso_1_code": null, "iso_3_code": "mfp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2898", "native_tokenizers": [], "scripts": [] }, { "name": "Minangkabau", "depth": 5, "iso_1_code": "ms", "iso_3_code": "min", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2899", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn", "Arab" ] }, { "name": "Malay, Kota Bangun Kutai", "depth": 5, "iso_1_code": "ms", "iso_3_code": "mqg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2900", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Sabah", "depth": 5, "iso_1_code": "ms", "iso_3_code": "msi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2901", "native_tokenizers": [], "scripts": [] }, { "name": "Musi", "depth": 5, "iso_1_code": "ms", "iso_3_code": "mui", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2902", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn" ] }, { "name": "Orang Kanaq", "depth": 5, "iso_1_code": "ms", "iso_3_code": "orn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2903", "native_tokenizers": [], "scripts": [] }, { "name": "Orang Seletar", "depth": 5, "iso_1_code": "ms", "iso_3_code": "ors", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2904", "native_tokenizers": [], "scripts": [] }, { "name": "Pekal", "depth": 5, "iso_1_code": "ms", "iso_3_code": "pel", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2905", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Central", "depth": 5, "iso_1_code": "ms", "iso_3_code": "pse", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2906", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn" ] }, { "name": "Temuan", "depth": 5, "iso_1_code": "ms", "iso_3_code": "tmw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2907", "native_tokenizers": [], "scripts": [] }, { "name": "Kaur", "depth": 5, "iso_1_code": "ms", "iso_3_code": "vkk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2908", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Tenggarong Kutai", "depth": 5, "iso_1_code": "ms", "iso_3_code": "vkt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2909", "native_tokenizers": [], "scripts": [] }, { "name": "Malay", "depth": 5, "iso_1_code": "ms", "iso_3_code": "zlm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2910", "native_tokenizers": [], "scripts": [] }, { "name": "Negeri Sembilan Malay", "depth": 5, "iso_1_code": "ms", "iso_3_code": "zmi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2911", "native_tokenizers": [], "scripts": [] }, { "name": "Malay, Standard", "depth": 5, "iso_1_code": "ms", "iso_3_code": "zsm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2912", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn", "Arab" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2879", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2869", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2849", "native_tokenizers": [], "scripts": [] }, { "name": "Minahasan", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tonsawang", "depth": 3, "iso_1_code": null, "iso_3_code": "tnw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2914", "native_tokenizers": [], "scripts": [] }, { "name": "North", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tontemboan", "depth": 4, "iso_1_code": null, "iso_3_code": "tnt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2916", "native_tokenizers": [], "scripts": [] }, { "name": "Northeast", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tondano", "depth": 5, "iso_1_code": null, "iso_3_code": "tdn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2918", "native_tokenizers": [], "scripts": [] }, { "name": "Tombulu", "depth": 5, "iso_1_code": null, "iso_3_code": "tom", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2919", "native_tokenizers": [], "scripts": [] }, { "name": "Tonsea", "depth": 5, "iso_1_code": null, "iso_3_code": "txs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2920", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2917", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2915", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2913", "native_tokenizers": [], "scripts": [] }, { "name": "Moklen", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Moklen", "depth": 3, "iso_1_code": null, "iso_3_code": "mkm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2922", "native_tokenizers": [], "scripts": [] }, { "name": "Moken", "depth": 3, "iso_1_code": null, "iso_3_code": "mwt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2923", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2921", "native_tokenizers": [], "scripts": [] }, { "name": "Nasal", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nasal", "depth": 3, "iso_1_code": null, "iso_3_code": "nsy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2925", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2924", "native_tokenizers": [], "scripts": [] }, { "name": "North Borneo", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Melanau-Kajang", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kajang", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bukitan", "depth": 5, "iso_1_code": null, "iso_3_code": "bkn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2929", "native_tokenizers": [], "scripts": [] }, { "name": "Kajaman", "depth": 5, "iso_1_code": null, "iso_3_code": "kag", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2930", "native_tokenizers": [], "scripts": [] }, { "name": "Lahanan", "depth": 5, "iso_1_code": null, "iso_3_code": "lhn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2931", "native_tokenizers": [], "scripts": [] }, { "name": "Punan Batu", "depth": 5, "iso_1_code": null, "iso_3_code": "pnm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2932", "native_tokenizers": [], "scripts": [] }, { "name": "Sekapan", "depth": 5, "iso_1_code": null, "iso_3_code": "skp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2933", "native_tokenizers": [], "scripts": [] }, { "name": "Sihan", "depth": 5, "iso_1_code": null, "iso_3_code": "spg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2934", "native_tokenizers": [], "scripts": [] }, { "name": "Ukit", "depth": 5, "iso_1_code": null, "iso_3_code": "umi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2935", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2928", "native_tokenizers": [], "scripts": [] }, { "name": "Melanau", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Melanau, Daro-Matu", "depth": 5, "iso_1_code": null, "iso_3_code": "dro", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2937", "native_tokenizers": [], "scripts": [] }, { "name": "Melanau, Kanowit-Tanjong", "depth": 5, "iso_1_code": null, "iso_3_code": "kxn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2938", "native_tokenizers": [], "scripts": [] }, { "name": "Melanau, Central", "depth": 5, "iso_1_code": null, "iso_3_code": "mel", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2939", "native_tokenizers": [], "scripts": [] }, { "name": "Melanau, Sibu", "depth": 5, "iso_1_code": null, "iso_3_code": "sdx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2940", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2936", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2927", "native_tokenizers": [], "scripts": [] }, { "name": "North Sarawakan", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Berawan-Lower Baram", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Berawan", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Berawan, West", "depth": 6, "iso_1_code": null, "iso_3_code": "zbw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2944", "native_tokenizers": [], "scripts": [] }, { "name": "Central-East Berawan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Berawan, Central", "depth": 7, "iso_1_code": null, "iso_3_code": "zbc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2946", "native_tokenizers": [], "scripts": [] }, { "name": "Berawan, East", "depth": 7, "iso_1_code": null, "iso_3_code": "zbe", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2947", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2945", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2943", "native_tokenizers": [], "scripts": [] }, { "name": "Lower Baram", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Belait", "depth": 8, "iso_1_code": null, "iso_3_code": "beg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2951", "native_tokenizers": [], "scripts": [] }, { "name": "Kiput", "depth": 8, "iso_1_code": null, "iso_3_code": "kyi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2952", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2950", "native_tokenizers": [], "scripts": [] }, { "name": "B", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lelak", "depth": 8, "iso_1_code": null, "iso_3_code": "llk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2954", "native_tokenizers": [], "scripts": [] }, { "name": "Narom", "depth": 8, "iso_1_code": null, "iso_3_code": "nrm", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2955", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tutong", "depth": 8, "iso_1_code": null, "iso_3_code": "ttg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2956", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2953", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2949", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2948", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2942", "native_tokenizers": [], "scripts": [] }, { "name": "Bintulu", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Vaie", "depth": 5, "iso_1_code": null, "iso_3_code": "bny", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2958", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2957", "native_tokenizers": [], "scripts": [] }, { "name": "Dayic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kelabitic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kelabit", "depth": 6, "iso_1_code": null, "iso_3_code": "kzi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2961", "native_tokenizers": [], "scripts": [] }, { "name": "Lengilu", "depth": 6, "iso_1_code": null, "iso_3_code": "lgi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2962", "native_tokenizers": [], "scripts": [] }, { "name": "Lundayeh", "depth": 6, "iso_1_code": null, "iso_3_code": "lnd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2963", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Putoh", "depth": 6, "iso_1_code": null, "iso_3_code": "put", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2964", "native_tokenizers": [], "scripts": [] }, { "name": "Sa\u2019ban", "depth": 6, "iso_1_code": null, "iso_3_code": "snv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2965", "native_tokenizers": [], "scripts": [] }, { "name": "Tring", "depth": 6, "iso_1_code": null, "iso_3_code": "tgq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2966", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2960", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2959", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan-Kenyah", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayanic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayan Proper", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayan, Busang", "depth": 7, "iso_1_code": null, "iso_3_code": "bfg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2970", "native_tokenizers": [], "scripts": [] }, { "name": "Bahau", "depth": 7, "iso_1_code": null, "iso_3_code": "bhv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2971", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan, Baram", "depth": 7, "iso_1_code": null, "iso_3_code": "kys", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2972", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan, Rejang", "depth": 7, "iso_1_code": null, "iso_3_code": "ree", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2973", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan, Wahau", "depth": 7, "iso_1_code": null, "iso_3_code": "whu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2974", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan Mahakam", "depth": 7, "iso_1_code": null, "iso_3_code": "xay", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2975", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan, Mendalam", "depth": 7, "iso_1_code": null, "iso_3_code": "xkd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2976", "native_tokenizers": [], "scripts": [] }, { "name": "Kayan, Kayan River", "depth": 7, "iso_1_code": null, "iso_3_code": "xkn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2977", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2969", "native_tokenizers": [], "scripts": [] }, { "name": "Modang", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Modang", "depth": 7, "iso_1_code": null, "iso_3_code": "mxd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2979", "native_tokenizers": [], "scripts": [] }, { "name": "Segai", "depth": 7, "iso_1_code": null, "iso_3_code": "sge", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2980", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2978", "native_tokenizers": [], "scripts": [] }, { "name": "Muller-Schwaner \u2018Punan\u2019", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bukat", "depth": 7, "iso_1_code": null, "iso_3_code": "bvk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2982", "native_tokenizers": [], "scripts": [] }, { "name": "Hovongan", "depth": 7, "iso_1_code": null, "iso_3_code": "hov", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2983", "native_tokenizers": [], "scripts": [] }, { "name": "Aoheng", "depth": 7, "iso_1_code": null, "iso_3_code": "pni", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2984", "native_tokenizers": [], "scripts": [] }, { "name": "Punan Aput", "depth": 7, "iso_1_code": null, "iso_3_code": "pud", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2985", "native_tokenizers": [], "scripts": [] }, { "name": "Punan Merah", "depth": 7, "iso_1_code": null, "iso_3_code": "puf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2986", "native_tokenizers": [], "scripts": [] }, { "name": "Kereho", "depth": 7, "iso_1_code": null, "iso_3_code": "xke", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2987", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2981", "native_tokenizers": [], "scripts": [] }, { "name": "Murik Kayan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Murik", "depth": 7, "iso_1_code": null, "iso_3_code": "mxr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2989", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2988", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2968", "native_tokenizers": [], "scripts": [] }, { "name": "Kenyah", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kenyah, Mainstream", "depth": 6, "iso_1_code": null, "iso_3_code": "xkl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2991", "native_tokenizers": [], "scripts": [] }, { "name": "Kayanic Kenyah", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sebop", "depth": 7, "iso_1_code": null, "iso_3_code": "sib", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2993", "native_tokenizers": [], "scripts": [] }, { "name": "Long Wat", "depth": 7, "iso_1_code": null, "iso_3_code": "ttw", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2994", "native_tokenizers": [], "scripts": [] }, { "name": "Kenyah, Wahau", "depth": 7, "iso_1_code": null, "iso_3_code": "whk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2995", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2992", "native_tokenizers": [], "scripts": [] }, { "name": "Upper Pujungan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Uma\u2019 Lung", "depth": 7, "iso_1_code": null, "iso_3_code": "ulu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2997", "native_tokenizers": [], "scripts": [] }, { "name": "Uma\u2019 Lasan", "depth": 7, "iso_1_code": null, "iso_3_code": "xky", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "2998", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "2996", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2990", "native_tokenizers": [], "scripts": [] }, { "name": "Penan", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Penan, Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": "pez", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3000", "native_tokenizers": [], "scripts": [] }, { "name": "Penan, Western", "depth": 6, "iso_1_code": null, "iso_3_code": "pne", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3001", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2999", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2967", "native_tokenizers": [], "scripts": [] }, { "name": "Punan Tubu", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Punan Tubu", "depth": 5, "iso_1_code": null, "iso_3_code": "puj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3003", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3002", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2941", "native_tokenizers": [], "scripts": [] }, { "name": "Rejang-Sajau", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Basap", "depth": 4, "iso_1_code": null, "iso_3_code": "bdb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3005", "native_tokenizers": [], "scripts": [] }, { "name": "Burusu", "depth": 4, "iso_1_code": null, "iso_3_code": "bqr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3006", "native_tokenizers": [], "scripts": [] }, { "name": "Punan Bah-Biau", "depth": 4, "iso_1_code": null, "iso_3_code": "pna", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3007", "native_tokenizers": [], "scripts": [] }, { "name": "Punan Merap", "depth": 4, "iso_1_code": null, "iso_3_code": "puc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3008", "native_tokenizers": [], "scripts": [] }, { "name": "Sajau Basap", "depth": 4, "iso_1_code": null, "iso_3_code": "sjb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3009", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3004", "native_tokenizers": [], "scripts": [] }, { "name": "Sabahan", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dusunic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bisaya-Lotud", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bisaya, Sabah", "depth": 6, "iso_1_code": null, "iso_3_code": "bsy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3013", "native_tokenizers": [], "scripts": [] }, { "name": "Lotud", "depth": 6, "iso_1_code": null, "iso_3_code": "dtr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3014", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bisaya, Brunei", "depth": 7, "iso_1_code": null, "iso_3_code": "bsb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3016", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3015", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3012", "native_tokenizers": [], "scripts": [] }, { "name": "Dusun", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kuijau", "depth": 6, "iso_1_code": null, "iso_3_code": "dkr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3018", "native_tokenizers": [], "scripts": [] }, { "name": "Rungus", "depth": 6, "iso_1_code": null, "iso_3_code": "drg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3019", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kota Marudu Talantang", "depth": 6, "iso_1_code": null, "iso_3_code": "grm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3020", "native_tokenizers": [], "scripts": [] }, { "name": "Kimaragang", "depth": 6, "iso_1_code": null, "iso_3_code": "kqr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3021", "native_tokenizers": [], "scripts": [] }, { "name": "Kadazan, Klias River", "depth": 6, "iso_1_code": null, "iso_3_code": "kqt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3022", "native_tokenizers": [], "scripts": [] }, { "name": "Tobilung", "depth": 6, "iso_1_code": null, "iso_3_code": "tgb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3023", "native_tokenizers": [], "scripts": [] }, { "name": "Central", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kadazan Dusun", "depth": 7, "iso_1_code": null, "iso_3_code": "dtp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3025", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sugut Dusun", "depth": 7, "iso_1_code": null, "iso_3_code": "kzs", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3026", "native_tokenizers": [], "scripts": [] }, { "name": "Minokok", "depth": 7, "iso_1_code": null, "iso_3_code": "mqq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3027", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3024", "native_tokenizers": [], "scripts": [] }, { "name": "Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kadazan, Labuk-Kinabatangan", "depth": 7, "iso_1_code": null, "iso_3_code": "dtb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3029", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3028", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3017", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dumpas", "depth": 6, "iso_1_code": null, "iso_3_code": "dmv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3031", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3030", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3011", "native_tokenizers": [], "scripts": [] }, { "name": "Ida\u2019an", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ida\u2019an", "depth": 5, "iso_1_code": null, "iso_3_code": "dbj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3033", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3032", "native_tokenizers": [], "scripts": [] }, { "name": "Murutic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Murut", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Okolod", "depth": 6, "iso_1_code": null, "iso_3_code": "kqv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3036", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Keningau", "depth": 6, "iso_1_code": null, "iso_3_code": "kxi", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3037", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Tahol", "depth": 6, "iso_1_code": null, "iso_3_code": "mvv", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3038", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Paluan", "depth": 6, "iso_1_code": null, "iso_3_code": "plz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3039", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Selungai", "depth": 6, "iso_1_code": null, "iso_3_code": "slg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3040", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Timugon", "depth": 6, "iso_1_code": null, "iso_3_code": "tih", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3041", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3035", "native_tokenizers": [], "scripts": [] }, { "name": "Northern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Murut, Bookan", "depth": 6, "iso_1_code": null, "iso_3_code": "bnb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3043", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3042", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Murut, Kalabakan", "depth": 6, "iso_1_code": null, "iso_3_code": "kve", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3045", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Sembakung", "depth": 6, "iso_1_code": null, "iso_3_code": "sbr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3046", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3044", "native_tokenizers": [], "scripts": [] }, { "name": "Tidung", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tidung, Southern", "depth": 6, "iso_1_code": null, "iso_3_code": "itd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3048", "native_tokenizers": [], "scripts": [] }, { "name": "Tidung, Northern", "depth": 6, "iso_1_code": null, "iso_3_code": "ntd", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3049", "native_tokenizers": [], "scripts": [] }, { "name": "Murut, Serudung", "depth": 6, "iso_1_code": null, "iso_3_code": "srk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3050", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3047", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Papar", "depth": 6, "iso_1_code": null, "iso_3_code": "dpp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3052", "native_tokenizers": [], "scripts": [] }, { "name": "Gana", "depth": 6, "iso_1_code": null, "iso_3_code": "gnq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3053", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3051", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3034", "native_tokenizers": [], "scripts": [] }, { "name": "Paitanic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Abai Sungai", "depth": 5, "iso_1_code": null, "iso_3_code": "abf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3055", "native_tokenizers": [], "scripts": [] }, { "name": "Tombonuo", "depth": 5, "iso_1_code": null, "iso_3_code": "txa", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3056", "native_tokenizers": [], "scripts": [] }, { "name": "Upper Kinabatangan", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kinabatangan, Upper", "depth": 6, "iso_1_code": null, "iso_3_code": "dmg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3058", "native_tokenizers": [], "scripts": [] }, { "name": "Lobu, Tampias", "depth": 6, "iso_1_code": null, "iso_3_code": "low", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3059", "native_tokenizers": [], "scripts": [] }, { "name": "Lobu, Lanas", "depth": 6, "iso_1_code": null, "iso_3_code": "ruu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3060", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3057", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3054", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tatana", "depth": 5, "iso_1_code": null, "iso_3_code": "txx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3062", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3061", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3010", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "2926", "native_tokenizers": [], "scripts": [] }, { "name": "North Mangyan", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Alangan", "depth": 3, "iso_1_code": null, "iso_3_code": "alj", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3064", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Iraya", "depth": 3, "iso_1_code": null, "iso_3_code": "iry", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3065", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tadyawan", "depth": 3, "iso_1_code": null, "iso_3_code": "tdy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3066", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3063", "native_tokenizers": [], "scripts": [] }, { "name": "Northern Luzon", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arta", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arta", "depth": 4, "iso_1_code": null, "iso_3_code": "atz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3069", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3068", "native_tokenizers": [], "scripts": [] }, { "name": "Ilocano", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ilocano", "depth": 4, "iso_1_code": null, "iso_3_code": "ilo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3071", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3070", "native_tokenizers": [], "scripts": [] }, { "name": "Meso-Cordilleran", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Alta", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Alta, Southern", "depth": 5, "iso_1_code": null, "iso_3_code": "agy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3074", "native_tokenizers": [], "scripts": [] }, { "name": "Alta, Northern", "depth": 5, "iso_1_code": null, "iso_3_code": "aqn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3075", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3073", "native_tokenizers": [], "scripts": [] }, { "name": "South-Central Cordilleran", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Cordilleran", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Isinai", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Isinay", "depth": 7, "iso_1_code": null, "iso_3_code": "inn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3079", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3078", "native_tokenizers": [], "scripts": [] }, { "name": "North Central Cordilleran", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kalinga-Itneg", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Itneg", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Itneg, Binongan", "depth": 9, "iso_1_code": null, "iso_3_code": "itb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3083", "native_tokenizers": [], "scripts": [] }, { "name": "Itneg, Inlaud", "depth": 9, "iso_1_code": null, "iso_3_code": "iti", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3084", "native_tokenizers": [], "scripts": [] }, { "name": "Itneg, Maeng", "depth": 9, "iso_1_code": null, "iso_3_code": "itt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3085", "native_tokenizers": [], "scripts": [] }, { "name": "Itneg, Moyadan", "depth": 9, "iso_1_code": null, "iso_3_code": "ity", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3086", "native_tokenizers": [], "scripts": [] }, { "name": "Itneg, Masadiit", "depth": 9, "iso_1_code": null, "iso_3_code": "tis", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3087", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3082", "native_tokenizers": [], "scripts": [] }, { "name": "Kalinga", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kalinga, Vanaw", "depth": 9, "iso_1_code": null, "iso_3_code": "bjx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3089", "native_tokenizers": [], "scripts": [] }, { "name": "Kalinga, Mabaka Valley", "depth": 9, "iso_1_code": null, "iso_3_code": "kkg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3090", "native_tokenizers": [], "scripts": [] }, { "name": "Kalinga, Majukayang", "depth": 9, "iso_1_code": null, "iso_3_code": "kmd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3091", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kalinga, Limos", "depth": 9, "iso_1_code": null, "iso_3_code": "kmk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3092", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kalinga, Tanudan", "depth": 9, "iso_1_code": null, "iso_3_code": "kml", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3093", "native_tokenizers": [], "scripts": [] }, { "name": "Kalinga, Lubuagan", "depth": 9, "iso_1_code": null, "iso_3_code": "knb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3094", "native_tokenizers": [], "scripts": [] }, { "name": "Kalinga, Southern", "depth": 9, "iso_1_code": null, "iso_3_code": "ksc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3095", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kalinga, Butbut", "depth": 9, "iso_1_code": null, "iso_3_code": "kyb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3096", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3088", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3081", "native_tokenizers": [], "scripts": [] }, { "name": "Nuclear Cordilleran", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Balangaw", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Balangao", "depth": 9, "iso_1_code": null, "iso_3_code": "blw", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3099", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3098", "native_tokenizers": [], "scripts": [] }, { "name": "Bontok-Kankanay", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bontok", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bontok, Eastern", "depth": 10, "iso_1_code": null, "iso_3_code": "ebk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3102", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bontok, Central", "depth": 10, "iso_1_code": null, "iso_3_code": "lbk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3103", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bontok, Southern", "depth": 10, "iso_1_code": null, "iso_3_code": "obk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3104", "native_tokenizers": [], "scripts": [] }, { "name": "Bontok, Northern", "depth": 10, "iso_1_code": null, "iso_3_code": "rbk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3105", "native_tokenizers": [], "scripts": [] }, { "name": "Bontok, Southwestern", "depth": 10, "iso_1_code": null, "iso_3_code": "vbk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3106", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3101", "native_tokenizers": [], "scripts": [] }, { "name": "Kankanay", "depth": 9, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kankanaey", "depth": 10, "iso_1_code": null, "iso_3_code": "kne", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3108", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kankanay, Northern", "depth": 10, "iso_1_code": null, "iso_3_code": "xnn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3109", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3107", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3100", "native_tokenizers": [], "scripts": [] }, { "name": "Ifugaw", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ifugao, Amganad", "depth": 9, "iso_1_code": null, "iso_3_code": "ifa", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3111", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ifugao, Batad", "depth": 9, "iso_1_code": null, "iso_3_code": "ifb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3112", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ifugao, Tuwali", "depth": 9, "iso_1_code": null, "iso_3_code": "ifk", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3113", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ifugao, Mayoyao", "depth": 9, "iso_1_code": null, "iso_3_code": "ifu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3114", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3110", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3097", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3080", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3077", "native_tokenizers": [], "scripts": [] }, { "name": "Southern Cordilleran", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ilongot", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bogkalot", "depth": 7, "iso_1_code": null, "iso_3_code": "ilk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3117", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3116", "native_tokenizers": [], "scripts": [] }, { "name": "West Southern Cordilleran", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pangasinan", "depth": 7, "iso_1_code": null, "iso_3_code": "pag", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3119", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Nuclear Southern Cordilleran", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ibaloy", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ibaloi", "depth": 9, "iso_1_code": null, "iso_3_code": "ibl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3122", "native_tokenizers": [], "scripts": [] }, { "name": "I-wak", "depth": 9, "iso_1_code": null, "iso_3_code": "iwk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3123", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3121", "native_tokenizers": [], "scripts": [] }, { "name": "Kallahan", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kallahan, Keley-i", "depth": 9, "iso_1_code": null, "iso_3_code": "ify", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3125", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Kalanguya", "depth": 9, "iso_1_code": null, "iso_3_code": "kak", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3126", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3124", "native_tokenizers": [], "scripts": [] }, { "name": "Karaw", "depth": 8, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Karao", "depth": 9, "iso_1_code": null, "iso_3_code": "kyj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3128", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3127", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3120", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3118", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3115", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3076", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3072", "native_tokenizers": [], "scripts": [] }, { "name": "Northern Cordilleran", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cagayan Valley", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ibanagic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Atta, Pudtol", "depth": 6, "iso_1_code": null, "iso_3_code": "atp", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3132", "native_tokenizers": [], "scripts": [] }, { "name": "Atta, Pamplona", "depth": 6, "iso_1_code": null, "iso_3_code": "att", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3133", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Atta, Faire", "depth": 6, "iso_1_code": null, "iso_3_code": "azt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3134", "native_tokenizers": [], "scripts": [] }, { "name": "Ibanag", "depth": 6, "iso_1_code": null, "iso_3_code": "ibg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3135", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Itawit", "depth": 6, "iso_1_code": null, "iso_3_code": "itv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3136", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Yogad", "depth": 6, "iso_1_code": null, "iso_3_code": "yog", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3137", "native_tokenizers": [], "scripts": [] }, { "name": "Gaddangic", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agta, Central Cagayan", "depth": 7, "iso_1_code": null, "iso_3_code": "agt", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3139", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Gaddang", "depth": 7, "iso_1_code": null, "iso_3_code": "gad", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3140", "native_tokenizers": [], "scripts": [] }, { "name": "Ga\ua78cdang", "depth": 7, "iso_1_code": null, "iso_3_code": "gdg", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3141", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3138", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3131", "native_tokenizers": [], "scripts": [] }, { "name": "Isnag", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Isnag", "depth": 6, "iso_1_code": null, "iso_3_code": "isd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3143", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Adasen", "depth": 6, "iso_1_code": null, "iso_3_code": "tiu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3144", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3142", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3130", "native_tokenizers": [], "scripts": [] }, { "name": "Northeastern Luzon", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agta, Pahanan", "depth": 5, "iso_1_code": null, "iso_3_code": "apf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3146", "native_tokenizers": [], "scripts": [] }, { "name": "Paranan", "depth": 5, "iso_1_code": null, "iso_3_code": "prf", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3147", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Northern", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agta, Casiguran Dumagat", "depth": 6, "iso_1_code": null, "iso_3_code": "dgc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3149", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Agta, Dupaninan", "depth": 6, "iso_1_code": null, "iso_3_code": "duo", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3150", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Agta, Dicamay", "depth": 6, "iso_1_code": null, "iso_3_code": "duy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3151", "native_tokenizers": [], "scripts": [] }, { "name": "Kasiguranin", "depth": 6, "iso_1_code": null, "iso_3_code": "ksn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3152", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3148", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3145", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3129", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3067", "native_tokenizers": [], "scripts": [] }, { "name": "Northwest Sumatra-Barrier Islands", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Enggano", "depth": 3, "iso_1_code": null, "iso_3_code": "eno", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3154", "native_tokenizers": [], "scripts": [] }, { "name": "Gayo", "depth": 3, "iso_1_code": null, "iso_3_code": "gay", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3155", "native_tokenizers": [], "scripts": [] }, { "name": "Mentawai", "depth": 3, "iso_1_code": null, "iso_3_code": "mwv", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3156", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Simeulue", "depth": 3, "iso_1_code": null, "iso_3_code": "smr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3157", "native_tokenizers": [], "scripts": [] }, { "name": "Batak", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Batak Dairi", "depth": 5, "iso_1_code": null, "iso_3_code": "btd", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3160", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Batak Karo", "depth": 5, "iso_1_code": null, "iso_3_code": "btx", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3161", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Batak Alas-Kluet", "depth": 5, "iso_1_code": null, "iso_3_code": "btz", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3162", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3159", "native_tokenizers": [], "scripts": [] }, { "name": "Simalungan", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Batak Simalungun", "depth": 5, "iso_1_code": null, "iso_3_code": "bts", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3164", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3163", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Batak Angkola", "depth": 5, "iso_1_code": null, "iso_3_code": "akb", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3166", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Batak Toba", "depth": 5, "iso_1_code": null, "iso_3_code": "bbc", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3167", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Batak Mandailing", "depth": 5, "iso_1_code": null, "iso_3_code": "btm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3168", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3165", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3158", "native_tokenizers": [], "scripts": [] }, { "name": "Nias", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nias", "depth": 4, "iso_1_code": null, "iso_3_code": "nia", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3170", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Sikule", "depth": 4, "iso_1_code": null, "iso_3_code": "skh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3171", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3169", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3153", "native_tokenizers": [], "scripts": [] }, { "name": "Palauan", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Palauan", "depth": 3, "iso_1_code": null, "iso_3_code": "pau", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3173", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3172", "native_tokenizers": [], "scripts": [] }, { "name": "Rejang", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rejang", "depth": 3, "iso_1_code": null, "iso_3_code": "rej", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3175", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3174", "native_tokenizers": [], "scripts": [] }, { "name": "Sangiric", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northern", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sangil", "depth": 4, "iso_1_code": null, "iso_3_code": "snl", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3178", "native_tokenizers": [], "scripts": [] }, { "name": "Sangir", "depth": 4, "iso_1_code": null, "iso_3_code": "sxn", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3179", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Talaud", "depth": 4, "iso_1_code": null, "iso_3_code": "tld", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3180", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3177", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bantik", "depth": 4, "iso_1_code": null, "iso_3_code": "bnq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3182", "native_tokenizers": [], "scripts": [] }, { "name": "Ratahan", "depth": 4, "iso_1_code": null, "iso_3_code": "rth", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3183", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3181", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3176", "native_tokenizers": [], "scripts": [] }, { "name": "South Sulawesi", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bugis", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bugis", "depth": 4, "iso_1_code": null, "iso_3_code": "bug", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3186", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Koneq-koneq", "depth": 4, "iso_1_code": null, "iso_3_code": "cml", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3187", "native_tokenizers": [], "scripts": [] }, { "name": "Tamanic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Embaloh", "depth": 5, "iso_1_code": null, "iso_3_code": "emb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3189", "native_tokenizers": [], "scripts": [] }, { "name": "Taman", "depth": 5, "iso_1_code": null, "iso_3_code": "tmn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3190", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3188", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3185", "native_tokenizers": [], "scripts": [] }, { "name": "Lemolang", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Limola", "depth": 4, "iso_1_code": null, "iso_3_code": "ley", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3192", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3191", "native_tokenizers": [], "scripts": [] }, { "name": "Makassar", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bentong", "depth": 4, "iso_1_code": null, "iso_3_code": "bnu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3194", "native_tokenizers": [], "scripts": [] }, { "name": "Konjo, Coastal", "depth": 4, "iso_1_code": null, "iso_3_code": "kjc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3195", "native_tokenizers": [], "scripts": [] }, { "name": "Konjo, Highland", "depth": 4, "iso_1_code": null, "iso_3_code": "kjk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3196", "native_tokenizers": [], "scripts": [] }, { "name": "Makasar", "depth": 4, "iso_1_code": null, "iso_3_code": "mak", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3197", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Selayar", "depth": 4, "iso_1_code": null, "iso_3_code": "sly", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3198", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3193", "native_tokenizers": [], "scripts": [] }, { "name": "Northern", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mamuju", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mamuju", "depth": 5, "iso_1_code": null, "iso_3_code": "mqx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3201", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3200", "native_tokenizers": [], "scripts": [] }, { "name": "Mandar", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mandar", "depth": 5, "iso_1_code": null, "iso_3_code": "mdr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3203", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3202", "native_tokenizers": [], "scripts": [] }, { "name": "Masenrempulu", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Malimpung", "depth": 5, "iso_1_code": null, "iso_3_code": "mli", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3205", "native_tokenizers": [], "scripts": [] }, { "name": "Duri", "depth": 5, "iso_1_code": null, "iso_3_code": "mvp", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3206", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Enrekang", "depth": 5, "iso_1_code": null, "iso_3_code": "ptt", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3207", "native_tokenizers": [], "scripts": [] }, { "name": "Maiwa", "depth": 5, "iso_1_code": null, "iso_3_code": "wmm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3208", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3204", "native_tokenizers": [], "scripts": [] }, { "name": "Pitu Ulunna Salu", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aralle-Tabulahan", "depth": 5, "iso_1_code": null, "iso_3_code": "atq", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3210", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Dakka", "depth": 5, "iso_1_code": null, "iso_3_code": "dkk", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3211", "native_tokenizers": [], "scripts": [] }, { "name": "Pannei", "depth": 5, "iso_1_code": null, "iso_3_code": "pnc", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3212", "native_tokenizers": [], "scripts": [] }, { "name": "Bambam", "depth": 5, "iso_1_code": null, "iso_3_code": "ptu", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3213", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Ulumanda\u2019", "depth": 5, "iso_1_code": null, "iso_3_code": "ulm", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3214", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3209", "native_tokenizers": [], "scripts": [] }, { "name": "Toraja-Sa\u2019dan", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kalumpang", "depth": 5, "iso_1_code": null, "iso_3_code": "kli", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3216", "native_tokenizers": [], "scripts": [] }, { "name": "Mamasa", "depth": 5, "iso_1_code": null, "iso_3_code": "mqj", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3217", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Tae\u2019", "depth": 5, "iso_1_code": null, "iso_3_code": "rob", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3218", "native_tokenizers": [], "scripts": [] }, { "name": "Toraja-Sa\u2019dan", "depth": 5, "iso_1_code": null, "iso_3_code": "sda", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3219", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Talondo\u2019", "depth": 5, "iso_1_code": null, "iso_3_code": "tln", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3220", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3215", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3199", "native_tokenizers": [], "scripts": [] }, { "name": "Seko", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Seko Tengah", "depth": 4, "iso_1_code": null, "iso_3_code": "sko", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3222", "native_tokenizers": [], "scripts": [] }, { "name": "Seko Padang", "depth": 4, "iso_1_code": null, "iso_3_code": "skx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3223", "native_tokenizers": [], "scripts": [] }, { "name": "Panasuan", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Budong-Budong", "depth": 5, "iso_1_code": null, "iso_3_code": "bdx", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3225", "native_tokenizers": [], "scripts": [] }, { "name": "Panasuan", "depth": 5, "iso_1_code": null, "iso_3_code": "psn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3226", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3224", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3221", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3184", "native_tokenizers": [], "scripts": [] }, { "name": "Sundanese", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Badui", "depth": 3, "iso_1_code": null, "iso_3_code": "bac", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3228", "native_tokenizers": [], "scripts": [] }, { "name": "Sunda", "depth": 3, "iso_1_code": "su", "iso_3_code": "sun", "children": [], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3229", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "3227", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bulungan", "depth": 3, "iso_1_code": null, "iso_3_code": "blj", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3231", "native_tokenizers": [], "scripts": [] }, { "name": "Gorap", "depth": 3, "iso_1_code": null, "iso_3_code": "goq", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3232", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3230", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"ms\")", "original_lang_name": "malay", "original_lang_code": "msa", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1452", "native_tokenizers": [], "scripts": [] }, { "name": "Northwest Formosan", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pazeh", "depth": 2, "iso_1_code": null, "iso_3_code": "pzh", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3234", "native_tokenizers": [], "scripts": [] }, { "name": "Kulon", "depth": 2, "iso_1_code": null, "iso_3_code": "uon", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3235", "native_tokenizers": [], "scripts": [] }, { "name": "Saisiyat", "depth": 2, "iso_1_code": null, "iso_3_code": "xsy", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3236", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3233", "native_tokenizers": [], "scripts": [] }, { "name": "Paiwan", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Paiwan", "depth": 2, "iso_1_code": null, "iso_3_code": "pwn", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3238", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3237", "native_tokenizers": [], "scripts": [] }, { "name": "Puyuma", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Puyuma", "depth": 2, "iso_1_code": null, "iso_3_code": "pyu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3240", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3239", "native_tokenizers": [], "scripts": [] }, { "name": "Rukai", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rukai", "depth": 2, "iso_1_code": null, "iso_3_code": "dru", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3242", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3241", "native_tokenizers": [], "scripts": [] }, { "name": "Tsouic", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Saaroa", "depth": 2, "iso_1_code": null, "iso_3_code": "sxr", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3244", "native_tokenizers": [], "scripts": [] }, { "name": "Tsou", "depth": 2, "iso_1_code": null, "iso_3_code": "tsu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3245", "native_tokenizers": [], "scripts": [] }, { "name": "Kanakanabu", "depth": 2, "iso_1_code": null, "iso_3_code": "xnb", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3246", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3243", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ketangalan", "depth": 2, "iso_1_code": null, "iso_3_code": "kae", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3248", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3247", "native_tokenizers": [], "scripts": [] }, { "name": "Western Plains", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Western Plains", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Babuza", "depth": 3, "iso_1_code": null, "iso_3_code": "bzg", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3251", "native_tokenizers": [], "scripts": [] }, { "name": "Papora-Hoanya", "depth": 3, "iso_1_code": null, "iso_3_code": "ppu", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3252", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3250", "native_tokenizers": [], "scripts": [] }, { "name": "Thao", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Thao", "depth": 3, "iso_1_code": null, "iso_3_code": "ssf", "children": [], "family": "Austronesian", "tokenizers": {}, "node_i": "3254", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3253", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "3249", "native_tokenizers": [], "scripts": [] } ], "family": "Austronesian", "tokenizers": {}, "node_i": "1436", "native_tokenizers": [], "scripts": [] }