{ "name": "Austro-Asiatic", "depth": 0, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mon-Khmer", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aslian", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jah Hut", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jah Hut", "depth": 4, "iso_1_code": null, "iso_3_code": "jah", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1167", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1166", "native_tokenizers": [], "scripts": [] }, { "name": "North Aslian", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chewong", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cheq Wong", "depth": 5, "iso_1_code": null, "iso_3_code": "cwg", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1170", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1169", "native_tokenizers": [], "scripts": [] }, { "name": "Eastern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Batek", "depth": 5, "iso_1_code": null, "iso_3_code": "btq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1172", "native_tokenizers": [], "scripts": [] }, { "name": "Jehai", "depth": 5, "iso_1_code": null, "iso_3_code": "jhi", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1173", "native_tokenizers": [], "scripts": [] }, { "name": "Minriq", "depth": 5, "iso_1_code": null, "iso_3_code": "mnq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1174", "native_tokenizers": [], "scripts": [] }, { "name": "Mintil", "depth": 5, "iso_1_code": null, "iso_3_code": "mzt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1175", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1171", "native_tokenizers": [], "scripts": [] }, { "name": "Tonga", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ten\u2019edn", "depth": 5, "iso_1_code": null, "iso_3_code": "tnz", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1177", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1176", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kintaq", "depth": 5, "iso_1_code": null, "iso_3_code": "knq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1179", "native_tokenizers": [], "scripts": [] }, { "name": "Kensiu", "depth": 5, "iso_1_code": null, "iso_3_code": "kns", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1180", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1178", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1168", "native_tokenizers": [], "scripts": [] }, { "name": "Senoic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lanoh", "depth": 4, "iso_1_code": null, "iso_3_code": "lnh", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1182", "native_tokenizers": [], "scripts": [] }, { "name": "Sab\u00fcm", "depth": 4, "iso_1_code": null, "iso_3_code": "sbo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1183", "native_tokenizers": [], "scripts": [] }, { "name": "Semai", "depth": 4, "iso_1_code": null, "iso_3_code": "sea", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1184", "native_tokenizers": [], "scripts": [] }, { "name": "Semnam", "depth": 4, "iso_1_code": null, "iso_3_code": "ssm", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1185", "native_tokenizers": [], "scripts": [] }, { "name": "Temiar", "depth": 4, "iso_1_code": null, "iso_3_code": "tea", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1186", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1181", "native_tokenizers": [], "scripts": [] }, { "name": "South Aslian", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mah Meri", "depth": 4, "iso_1_code": null, "iso_3_code": "mhe", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1188", "native_tokenizers": [], "scripts": [] }, { "name": "Semelai", "depth": 4, "iso_1_code": null, "iso_3_code": "sza", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1189", "native_tokenizers": [], "scripts": [] }, { "name": "Semaq Beri", "depth": 4, "iso_1_code": null, "iso_3_code": "szc", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1190", "native_tokenizers": [], "scripts": [] }, { "name": "Temoq", "depth": 4, "iso_1_code": null, "iso_3_code": "tmo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1191", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1187", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1165", "native_tokenizers": [], "scripts": [] }, { "name": "Eastern Mon-Khmer", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bahnaric", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Bahnaric", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Alak", "depth": 5, "iso_1_code": null, "iso_3_code": "alk", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1195", "native_tokenizers": [], "scripts": [] }, { "name": "Bahnar", "depth": 5, "iso_1_code": null, "iso_3_code": "bdq", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1196", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Romam", "depth": 5, "iso_1_code": null, "iso_3_code": "rmx", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1197", "native_tokenizers": [], "scripts": [] }, { "name": "Tampuan", "depth": 5, "iso_1_code": null, "iso_3_code": "tpu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1198", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1194", "native_tokenizers": [], "scripts": [] }, { "name": "East Bahnaric", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cua", "depth": 5, "iso_1_code": null, "iso_3_code": "cua", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1200", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1199", "native_tokenizers": [], "scripts": [] }, { "name": "North Bahnaric", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Katua", "depth": 5, "iso_1_code": null, "iso_3_code": "kta", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1202", "native_tokenizers": [], "scripts": [] }, { "name": "Kachok", "depth": 5, "iso_1_code": null, "iso_3_code": "xkk", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1203", "native_tokenizers": [], "scripts": [] }, { "name": "East", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kayong", "depth": 6, "iso_1_code": null, "iso_3_code": "kxy", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1205", "native_tokenizers": [], "scripts": [] }, { "name": "Takua", "depth": 6, "iso_1_code": null, "iso_3_code": "tkz", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1206", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1204", "native_tokenizers": [], "scripts": [] }, { "name": "West", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Trieng", "depth": 6, "iso_1_code": null, "iso_3_code": "stg", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1208", "native_tokenizers": [], "scripts": [] }, { "name": "Talieng", "depth": 6, "iso_1_code": null, "iso_3_code": "tdf", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1209", "native_tokenizers": [], "scripts": [] }, { "name": "Duan", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Halang Doan", "depth": 7, "iso_1_code": null, "iso_3_code": "hld", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1211", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1210", "native_tokenizers": [], "scripts": [] }, { "name": "Jeh-Halang", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Halang", "depth": 7, "iso_1_code": null, "iso_3_code": "hal", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1213", "native_tokenizers": [], "scripts": [] }, { "name": "Jeh", "depth": 7, "iso_1_code": null, "iso_3_code": "jeh", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1214", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1212", "native_tokenizers": [], "scripts": [] }, { "name": "Rengao", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Rengao", "depth": 7, "iso_1_code": null, "iso_3_code": "ren", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1216", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1215", "native_tokenizers": [], "scripts": [] }, { "name": "Sedang-Todrah", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sedang", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hre", "depth": 8, "iso_1_code": null, "iso_3_code": "hre", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1219", "native_tokenizers": [], "scripts": [] }, { "name": "Sedang", "depth": 8, "iso_1_code": null, "iso_3_code": "sed", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1220", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1218", "native_tokenizers": [], "scripts": [] }, { "name": "Todrah-Monom", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Monom", "depth": 8, "iso_1_code": null, "iso_3_code": "moo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1222", "native_tokenizers": [], "scripts": [] }, { "name": "Todrah", "depth": 8, "iso_1_code": null, "iso_3_code": "tdr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1223", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1221", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1217", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1207", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1201", "native_tokenizers": [], "scripts": [] }, { "name": "South Bahnaric", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Stieng, Budeh", "depth": 5, "iso_1_code": null, "iso_3_code": "stt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1225", "native_tokenizers": [], "scripts": [] }, { "name": "Sre-Mnong", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mnong", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern Mnong", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mnong, Eastern", "depth": 8, "iso_1_code": null, "iso_3_code": "mng", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1229", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1228", "native_tokenizers": [], "scripts": [] }, { "name": "Southern-Central Mnong", "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mnong, Central", "depth": 8, "iso_1_code": null, "iso_3_code": "cmo", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1231", "native_tokenizers": [], "scripts": [ "Latn", "Khmr" ] }, { "name": "Mnong, Southern", "depth": 8, "iso_1_code": null, "iso_3_code": "mnn", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1232", "native_tokenizers": [], "scripts": [] }, { "name": "Kraol", "depth": 8, "iso_1_code": null, "iso_3_code": "rka", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1233", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1230", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1227", "native_tokenizers": [], "scripts": [] }, { "name": "Sre", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Maa", "depth": 7, "iso_1_code": null, "iso_3_code": "cma", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1235", "native_tokenizers": [], "scripts": [] }, { "name": "Koho", "depth": 7, "iso_1_code": null, "iso_3_code": "kpm", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1236", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1234", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1226", "native_tokenizers": [], "scripts": [] }, { "name": "Stieng-Chrau", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chrau", "depth": 6, "iso_1_code": null, "iso_3_code": "crw", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1238", "native_tokenizers": [], "scripts": [] }, { "name": "Mel-Khaonh", "depth": 6, "iso_1_code": null, "iso_3_code": "hkn", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1239", "native_tokenizers": [], "scripts": [] }, { "name": "Stieng, Bulo", "depth": 6, "iso_1_code": null, "iso_3_code": "sti", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1240", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1237", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1224", "native_tokenizers": [], "scripts": [] }, { "name": "West Bahnaric", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lavi", "depth": 5, "iso_1_code": null, "iso_3_code": "lvi", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1242", "native_tokenizers": [], "scripts": [] }, { "name": "Brao-Kravet", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Brao", "depth": 6, "iso_1_code": null, "iso_3_code": "brb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1244", "native_tokenizers": [], "scripts": [] }, { "name": "Krung", "depth": 6, "iso_1_code": null, "iso_3_code": "krr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1245", "native_tokenizers": [], "scripts": [] }, { "name": "Kavet", "depth": 6, "iso_1_code": null, "iso_3_code": "krv", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1246", "native_tokenizers": [], "scripts": [] }, { "name": "Sou", "depth": 6, "iso_1_code": null, "iso_3_code": "sqq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1247", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1243", "native_tokenizers": [], "scripts": [] }, { "name": "Laven", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Laven", "depth": 6, "iso_1_code": null, "iso_3_code": "lbo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1249", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1248", "native_tokenizers": [], "scripts": [] }, { "name": "Nyaheun", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nyaheun", "depth": 6, "iso_1_code": null, "iso_3_code": "nev", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1251", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1250", "native_tokenizers": [], "scripts": [] }, { "name": "Oi-The", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Oy", "depth": 6, "iso_1_code": null, "iso_3_code": "oyb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1253", "native_tokenizers": [], "scripts": [] }, { "name": "Sapuan", "depth": 6, "iso_1_code": null, "iso_3_code": "spu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1254", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1252", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1241", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1193", "native_tokenizers": [], "scripts": [] }, { "name": "Katuic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central Katuic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ta\u2019oih", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ir", "depth": 6, "iso_1_code": null, "iso_3_code": "irr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1258", "native_tokenizers": [], "scripts": [] }, { "name": "Ong", "depth": 6, "iso_1_code": null, "iso_3_code": "oog", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1259", "native_tokenizers": [], "scripts": [] }, { "name": "Ta\u2019oih, Upper", "depth": 6, "iso_1_code": null, "iso_3_code": "tth", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1260", "native_tokenizers": [], "scripts": [] }, { "name": "Ta\u2019oih, Lower", "depth": 6, "iso_1_code": null, "iso_3_code": "tto", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1261", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1257", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1256", "native_tokenizers": [], "scripts": [] }, { "name": "East Katuic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Katu-Pacoh", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Katu, Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": "ktv", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1264", "native_tokenizers": [], "scripts": [] }, { "name": "Katu, Western", "depth": 6, "iso_1_code": null, "iso_3_code": "kuf", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1265", "native_tokenizers": [], "scripts": [] }, { "name": "Pacoh", "depth": 6, "iso_1_code": null, "iso_3_code": "pac", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1266", "native_tokenizers": [], "scripts": [] }, { "name": "Phuong", "depth": 6, "iso_1_code": null, "iso_3_code": "phg", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1267", "native_tokenizers": [], "scripts": [] }, { "name": "Tareng", "depth": 6, "iso_1_code": null, "iso_3_code": "tgr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1268", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1263", "native_tokenizers": [], "scripts": [] }, { "name": "Ngeq-Nkriang", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kriang", "depth": 6, "iso_1_code": null, "iso_3_code": "ngt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1270", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1269", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1262", "native_tokenizers": [], "scripts": [] }, { "name": "West Katuic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bru", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bru, Eastern", "depth": 6, "iso_1_code": null, "iso_3_code": "bru", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1273", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Bru, Western", "depth": 6, "iso_1_code": null, "iso_3_code": "brv", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1274", "native_tokenizers": [], "scripts": [] }, { "name": "Katang, Northern", "depth": 6, "iso_1_code": null, "iso_3_code": "ncq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1275", "native_tokenizers": [], "scripts": [ "Laoo" ] }, { "name": "Katang, Southern", "depth": 6, "iso_1_code": null, "iso_3_code": "sct", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1276", "native_tokenizers": [], "scripts": [] }, { "name": "So", "depth": 6, "iso_1_code": null, "iso_3_code": "sss", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1277", "native_tokenizers": [], "scripts": [] }, { "name": "Khua", "depth": 6, "iso_1_code": null, "iso_3_code": "xhv", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1278", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1272", "native_tokenizers": [], "scripts": [] }, { "name": "Kuay", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kuay", "depth": 6, "iso_1_code": null, "iso_3_code": "kdt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1280", "native_tokenizers": [], "scripts": [] }, { "name": "Nyeu", "depth": 6, "iso_1_code": null, "iso_3_code": "nyl", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1281", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1279", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1271", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1255", "native_tokenizers": [], "scripts": [] }, { "name": "Khmer", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Khmer", "depth": 4, "iso_1_code": "km", "iso_3_code": "khm", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" } }, "node_i": "1283", "native_tokenizers": [ "Khmr" ], "scripts": [ "Khmr" ] }, { "name": "Khmer, Northern", "depth": 4, "iso_1_code": null, "iso_3_code": "kxm", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1284", "native_tokenizers": [], "scripts": [ "Thai" ] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" } }, "node_i": "1282", "native_tokenizers": [], "scripts": [] }, { "name": "Pearic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Pear", "depth": 5, "iso_1_code": null, "iso_3_code": "pcb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1287", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1286", "native_tokenizers": [], "scripts": [] }, { "name": "Western", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chong", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chong", "depth": 6, "iso_1_code": null, "iso_3_code": "cog", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1290", "native_tokenizers": [], "scripts": [] }, { "name": "Chung", "depth": 6, "iso_1_code": null, "iso_3_code": "scq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1291", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1289", "native_tokenizers": [], "scripts": [] }, { "name": "Samre", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Somray", "depth": 6, "iso_1_code": null, "iso_3_code": "smu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1293", "native_tokenizers": [], "scripts": [] }, { "name": "Samre", "depth": 6, "iso_1_code": null, "iso_3_code": "sxm", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1294", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1292", "native_tokenizers": [], "scripts": [] }, { "name": "Suoy", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Su\u2019ung", "depth": 6, "iso_1_code": null, "iso_3_code": "syo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1296", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1295", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1288", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1285", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1192", "native_tokenizers": [], "scripts": [] }, { "name": "Monic", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mon", "depth": 3, "iso_1_code": null, "iso_3_code": "mnw", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1298", "native_tokenizers": [], "scripts": [ "Mymr" ] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1297", "native_tokenizers": [], "scripts": [] }, { "name": "Nicobar", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Car", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nicobarese, Car", "depth": 4, "iso_1_code": null, "iso_3_code": "caq", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1301", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1300", "native_tokenizers": [], "scripts": [] }, { "name": "Chowra-Teressa", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chaura", "depth": 4, "iso_1_code": null, "iso_3_code": "crv", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1303", "native_tokenizers": [], "scripts": [] }, { "name": "Teressa", "depth": 4, "iso_1_code": null, "iso_3_code": "tef", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1304", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1302", "native_tokenizers": [], "scripts": [] }, { "name": "Great Nicobar", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nicobarese, Southern", "depth": 4, "iso_1_code": null, "iso_3_code": "nik", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1306", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1305", "native_tokenizers": [], "scripts": [] }, { "name": "Nancowry", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nicobarese, Central", "depth": 4, "iso_1_code": null, "iso_3_code": "ncb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1308", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1307", "native_tokenizers": [], "scripts": [] }, { "name": "Shom Peng", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Shom Peng", "depth": 4, "iso_1_code": null, "iso_3_code": "sii", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1310", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1309", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1299", "native_tokenizers": [], "scripts": [] }, { "name": "Northern Mon-Khmer", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Khasian", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "War-Jaintia", "depth": 4, "iso_1_code": null, "iso_3_code": "aml", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1313", "native_tokenizers": [], "scripts": [] }, { "name": "Khasi", "depth": 4, "iso_1_code": null, "iso_3_code": "kha", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1314", "native_tokenizers": [], "scripts": [ "Latn" ] }, { "name": "Lyngngam", "depth": 4, "iso_1_code": null, "iso_3_code": "lyg", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1315", "native_tokenizers": [], "scripts": [] }, { "name": "Pnar", "depth": 4, "iso_1_code": null, "iso_3_code": "pbv", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1316", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1312", "native_tokenizers": [], "scripts": [] }, { "name": "Khmuic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Khao", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Khao", "depth": 5, "iso_1_code": null, "iso_3_code": "xao", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1319", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1318", "native_tokenizers": [], "scripts": [] }, { "name": "Mal-Khmu\u2019", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Khmu\u2019", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Khuen", "depth": 6, "iso_1_code": null, "iso_3_code": "khf", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1322", "native_tokenizers": [], "scripts": [] }, { "name": "Khmu", "depth": 6, "iso_1_code": null, "iso_3_code": "kjg", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1323", "native_tokenizers": [], "scripts": [] }, { "name": "O\u2019du", "depth": 6, "iso_1_code": null, "iso_3_code": "tyh", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1324", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1321", "native_tokenizers": [], "scripts": [] }, { "name": "Mal-Prai", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mal", "depth": 6, "iso_1_code": null, "iso_3_code": "mlf", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1326", "native_tokenizers": [], "scripts": [] }, { "name": "Prai", "depth": 6, "iso_1_code": null, "iso_3_code": "prt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1327", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1325", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1320", "native_tokenizers": [], "scripts": [] }, { "name": "Mlabri", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mlabri", "depth": 5, "iso_1_code": null, "iso_3_code": "mra", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1329", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1328", "native_tokenizers": [], "scripts": [] }, { "name": "Xinh Mul", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Phong-Kniang", "depth": 5, "iso_1_code": null, "iso_3_code": "pnx", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1331", "native_tokenizers": [], "scripts": [] }, { "name": "Puoc", "depth": 5, "iso_1_code": null, "iso_3_code": "puo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1332", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1330", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1317", "native_tokenizers": [], "scripts": [] }, { "name": "Mang", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mang", "depth": 4, "iso_1_code": null, "iso_3_code": "zng", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1334", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1333", "native_tokenizers": [], "scripts": [] }, { "name": "Palaungic", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern Palaungic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Angkuic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hu", "depth": 6, "iso_1_code": null, "iso_3_code": "huo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1338", "native_tokenizers": [], "scripts": [] }, { "name": "Kon Keu", "depth": 6, "iso_1_code": null, "iso_3_code": "kkn", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1339", "native_tokenizers": [], "scripts": [] }, { "name": "Man Met", "depth": 6, "iso_1_code": null, "iso_3_code": "mml", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1340", "native_tokenizers": [], "scripts": [] }, { "name": "Mok", "depth": 6, "iso_1_code": null, "iso_3_code": "mqt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1341", "native_tokenizers": [], "scripts": [] }, { "name": "Samtao", "depth": 6, "iso_1_code": null, "iso_3_code": "stu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1342", "native_tokenizers": [], "scripts": [] }, { "name": "Tai Loi", "depth": 6, "iso_1_code": null, "iso_3_code": "tlq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1343", "native_tokenizers": [], "scripts": [] }, { "name": "Muak Sa-aak", "depth": 6, "iso_1_code": null, "iso_3_code": "ukk", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1344", "native_tokenizers": [], "scripts": [] }, { "name": "U", "depth": 6, "iso_1_code": null, "iso_3_code": "uuu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1345", "native_tokenizers": [], "scripts": [] }, { "name": "Kiorr", "depth": 6, "iso_1_code": null, "iso_3_code": "xko", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1346", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1337", "native_tokenizers": [], "scripts": [] }, { "name": "Bit-Khang", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bit", "depth": 6, "iso_1_code": null, "iso_3_code": "bgk", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1348", "native_tokenizers": [], "scripts": [] }, { "name": "Bumang", "depth": 6, "iso_1_code": null, "iso_3_code": "bvp", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1349", "native_tokenizers": [], "scripts": [] }, { "name": "Kh\u00e1ng", "depth": 6, "iso_1_code": null, "iso_3_code": "kjm", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1350", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1347", "native_tokenizers": [], "scripts": [] }, { "name": "Lametic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Con", "depth": 6, "iso_1_code": null, "iso_3_code": "cno", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1352", "native_tokenizers": [], "scripts": [] }, { "name": "Rmeet", "depth": 6, "iso_1_code": null, "iso_3_code": "lbn", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1353", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1351", "native_tokenizers": [], "scripts": [] }, { "name": "Waic", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bulang", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Blang", "depth": 7, "iso_1_code": null, "iso_3_code": "blr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1356", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1355", "native_tokenizers": [], "scripts": [] }, { "name": "Lawa", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lawa, Western", "depth": 7, "iso_1_code": null, "iso_3_code": "lcp", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1358", "native_tokenizers": [], "scripts": [ "Thai" ] }, { "name": "Lawa, Eastern", "depth": 7, "iso_1_code": null, "iso_3_code": "lwl", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1359", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1357", "native_tokenizers": [], "scripts": [] }, { "name": "Wa", "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Wa, Parauk", "depth": 7, "iso_1_code": null, "iso_3_code": "prk", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1361", "native_tokenizers": [], "scripts": [] }, { "name": "Awa", "depth": 7, "iso_1_code": null, "iso_3_code": "vwa", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1362", "native_tokenizers": [], "scripts": [] }, { "name": "Wa, Vo", "depth": 7, "iso_1_code": null, "iso_3_code": "wbm", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1363", "native_tokenizers": [], "scripts": [ "Latn" ] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1360", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1354", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1336", "native_tokenizers": [], "scripts": [] }, { "name": "Western Palaungic", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Danau", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Danau", "depth": 6, "iso_1_code": null, "iso_3_code": "dnu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1366", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1365", "native_tokenizers": [], "scripts": [] }, { "name": "Palaung", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Palaung, Ruching", "depth": 6, "iso_1_code": null, "iso_3_code": "pce", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1368", "native_tokenizers": [], "scripts": [] }, { "name": "Palaung, Shwe", "depth": 6, "iso_1_code": null, "iso_3_code": "pll", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1369", "native_tokenizers": [], "scripts": [] }, { "name": "Palaung, Rumai", "depth": 6, "iso_1_code": null, "iso_3_code": "rbb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1370", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1367", "native_tokenizers": [], "scripts": [] }, { "name": "Riang", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Riang Lang", "depth": 6, "iso_1_code": null, "iso_3_code": "ril", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1372", "native_tokenizers": [], "scripts": [] }, { "name": "Riang Lai", "depth": 6, "iso_1_code": null, "iso_3_code": "yin", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1373", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1371", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1364", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1335", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1311", "native_tokenizers": [], "scripts": [] }, { "name": "Palyu", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bugan", "depth": 3, "iso_1_code": null, "iso_3_code": "bbh", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1375", "native_tokenizers": [], "scripts": [] }, { "name": "Bolyu", "depth": 3, "iso_1_code": null, "iso_3_code": "ply", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1376", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1374", "native_tokenizers": [], "scripts": [] }, { "name": "Southern Monic", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nyahkur", "depth": 3, "iso_1_code": null, "iso_3_code": "cbn", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1378", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1377", "native_tokenizers": [], "scripts": [] }, { "name": "Unclassified", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kemiehua", "depth": 3, "iso_1_code": null, "iso_3_code": "kfj", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1380", "native_tokenizers": [], "scripts": [] }, { "name": "Kuanhua", "depth": 3, "iso_1_code": null, "iso_3_code": "xnh", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1381", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1379", "native_tokenizers": [], "scripts": [] }, { "name": "Viet-Muong", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chut", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arem", "depth": 4, "iso_1_code": null, "iso_3_code": "aem", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1384", "native_tokenizers": [], "scripts": [] }, { "name": "Maleng", "depth": 4, "iso_1_code": null, "iso_3_code": "pkt", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1385", "native_tokenizers": [], "scripts": [] }, { "name": "Chut", "depth": 4, "iso_1_code": null, "iso_3_code": "scb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1386", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1383", "native_tokenizers": [], "scripts": [] }, { "name": "Cuoi", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hung", "depth": 4, "iso_1_code": null, "iso_3_code": "hnu", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1388", "native_tokenizers": [], "scripts": [] }, { "name": "Tho", "depth": 4, "iso_1_code": null, "iso_3_code": "tou", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1389", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1387", "native_tokenizers": [], "scripts": [] }, { "name": "Muong", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bo", "depth": 4, "iso_1_code": null, "iso_3_code": "bgl", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1391", "native_tokenizers": [], "scripts": [] }, { "name": "Muong", "depth": 4, "iso_1_code": null, "iso_3_code": "mtq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1392", "native_tokenizers": [], "scripts": [] }, { "name": "Ngu\u00f4n", "depth": 4, "iso_1_code": null, "iso_3_code": "nuo", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1393", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1390", "native_tokenizers": [], "scripts": [] }, { "name": "Thavung", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aheu", "depth": 4, "iso_1_code": null, "iso_3_code": "thm", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1395", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1394", "native_tokenizers": [], "scripts": [] }, { "name": "Vietnamese", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Vietnamese", "depth": 4, "iso_1_code": "vi", "iso_3_code": "vie", "children": [], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1397", "native_tokenizers": [ "Latn" ], "scripts": [ "Latn" ] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1396", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1382", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": { "Khmr": { "full_object": "KhmerTokenizer()", "original_lang_name": "khmer", "original_lang_code": "khm", "script": "Khmr", "class_name": "KhmerTokenizer" }, "Latn": { "full_object": "SpaCyTokenizer(\"vi\")", "original_lang_name": "vietnamese", "original_lang_code": "vie", "script": "Latn", "class_name": "SpaCyTokenizer" } }, "node_i": "1164", "native_tokenizers": [], "scripts": [] }, { "name": "Munda", "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North Munda", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kherwari", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Agariya", "depth": 4, "iso_1_code": null, "iso_3_code": "agi", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1401", "native_tokenizers": [], "scripts": [] }, { "name": "Bijori", "depth": 4, "iso_1_code": null, "iso_3_code": "bix", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1402", "native_tokenizers": [], "scripts": [] }, { "name": "Kodaku", "depth": 4, "iso_1_code": null, "iso_3_code": "ksz", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1403", "native_tokenizers": [], "scripts": [] }, { "name": "Mundari", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Asuri", "depth": 5, "iso_1_code": null, "iso_3_code": "asr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1405", "native_tokenizers": [], "scripts": [] }, { "name": "Birhor", "depth": 5, "iso_1_code": null, "iso_3_code": "biy", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1406", "native_tokenizers": [], "scripts": [] }, { "name": "Koda", "depth": 5, "iso_1_code": null, "iso_3_code": "cdz", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1407", "native_tokenizers": [], "scripts": [] }, { "name": "Kol", "depth": 5, "iso_1_code": null, "iso_3_code": "ekl", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1408", "native_tokenizers": [], "scripts": [] }, { "name": "Ho", "depth": 5, "iso_1_code": null, "iso_3_code": "hoc", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1409", "native_tokenizers": [], "scripts": [ "Latn", "Wara" ] }, { "name": "Korwa", "depth": 5, "iso_1_code": null, "iso_3_code": "kfp", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1410", "native_tokenizers": [], "scripts": [] }, { "name": "Mundari", "depth": 5, "iso_1_code": null, "iso_3_code": "unr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1411", "native_tokenizers": [], "scripts": [] }, { "name": "Munda", "depth": 5, "iso_1_code": null, "iso_3_code": "unx", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1412", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1404", "native_tokenizers": [], "scripts": [] }, { "name": "Santali", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mahali", "depth": 5, "iso_1_code": null, "iso_3_code": "mjx", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1414", "native_tokenizers": [], "scripts": [] }, { "name": "Santhali", "depth": 5, "iso_1_code": null, "iso_3_code": "sat", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1415", "native_tokenizers": [], "scripts": [ "Latn", "Olck" ] }, { "name": "Turi", "depth": 5, "iso_1_code": null, "iso_3_code": "trd", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1416", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1413", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1400", "native_tokenizers": [], "scripts": [] }, { "name": "Korku", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Korku", "depth": 4, "iso_1_code": null, "iso_3_code": "kfq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1418", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1417", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1399", "native_tokenizers": [], "scripts": [] }, { "name": "South Munda", "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kharia-Juang", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Juang", "depth": 4, "iso_1_code": null, "iso_3_code": "jun", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1421", "native_tokenizers": [], "scripts": [ "Orya" ] }, { "name": "Kharia", "depth": 4, "iso_1_code": null, "iso_3_code": "khr", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1422", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1420", "native_tokenizers": [], "scripts": [] }, { "name": "Koraput Munda", "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gutob-Remo-Geta\u2019", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Geta\u2019", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gata\u2019", "depth": 6, "iso_1_code": null, "iso_3_code": "gaq", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1426", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1425", "native_tokenizers": [], "scripts": [] }, { "name": "Gutob-Remo", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bondo", "depth": 6, "iso_1_code": null, "iso_3_code": "bfw", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1428", "native_tokenizers": [], "scripts": [] }, { "name": "Gadaba, Bodo", "depth": 6, "iso_1_code": null, "iso_3_code": "gbj", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1429", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1427", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1424", "native_tokenizers": [], "scripts": [] }, { "name": "Sora-Juray-Gorum", "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gorum", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Parenga", "depth": 6, "iso_1_code": null, "iso_3_code": "pcj", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1432", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1431", "native_tokenizers": [], "scripts": [] }, { "name": "Sora-Juray", "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Juray", "depth": 6, "iso_1_code": null, "iso_3_code": "juy", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1434", "native_tokenizers": [], "scripts": [] }, { "name": "Sora", "depth": 6, "iso_1_code": null, "iso_3_code": "srb", "children": [], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1435", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1433", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1430", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1423", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1419", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1398", "native_tokenizers": [], "scripts": [] } ], "family": "Austro-Asiatic", "tokenizers": {}, "node_i": "1163", "native_tokenizers": [], "scripts": [] }