Spaces:
Paused
Paused
File size: 7,334 Bytes
d66c48f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 |
"""from https://github.com/Plachtaa/VALL-E-X/g2p"""
import re
import jieba
import cn2an
# List of (Latin alphabet, bopomofo) pairs:
_latin_to_bopomofo = [
(re.compile("%s" % x[0], re.IGNORECASE), x[1])
for x in [
("a", "ㄟˉ"),
("b", "ㄅㄧˋ"),
("c", "ㄙㄧˉ"),
("d", "ㄉㄧˋ"),
("e", "ㄧˋ"),
("f", "ㄝˊㄈㄨˋ"),
("g", "ㄐㄧˋ"),
("h", "ㄝˇㄑㄩˋ"),
("i", "ㄞˋ"),
("j", "ㄐㄟˋ"),
("k", "ㄎㄟˋ"),
("l", "ㄝˊㄛˋ"),
("m", "ㄝˊㄇㄨˋ"),
("n", "ㄣˉ"),
("o", "ㄡˉ"),
("p", "ㄆㄧˉ"),
("q", "ㄎㄧㄡˉ"),
("r", "ㄚˋ"),
("s", "ㄝˊㄙˋ"),
("t", "ㄊㄧˋ"),
("u", "ㄧㄡˉ"),
("v", "ㄨㄧˉ"),
("w", "ㄉㄚˋㄅㄨˋㄌㄧㄡˋ"),
("x", "ㄝˉㄎㄨˋㄙˋ"),
("y", "ㄨㄞˋ"),
("z", "ㄗㄟˋ"),
]
]
# List of (bopomofo, romaji) pairs:
_bopomofo_to_romaji = [
(re.compile("%s" % x[0]), x[1])
for x in [
("ㄅㄛ", "p⁼wo"),
("ㄆㄛ", "pʰwo"),
("ㄇㄛ", "mwo"),
("ㄈㄛ", "fwo"),
("ㄅ", "p⁼"),
("ㄆ", "pʰ"),
("ㄇ", "m"),
("ㄈ", "f"),
("ㄉ", "t⁼"),
("ㄊ", "tʰ"),
("ㄋ", "n"),
("ㄌ", "l"),
("ㄍ", "k⁼"),
("ㄎ", "kʰ"),
("ㄏ", "h"),
("ㄐ", "ʧ⁼"),
("ㄑ", "ʧʰ"),
("ㄒ", "ʃ"),
("ㄓ", "ʦ`⁼"),
("ㄔ", "ʦ`ʰ"),
("ㄕ", "s`"),
("ㄖ", "ɹ`"),
("ㄗ", "ʦ⁼"),
("ㄘ", "ʦʰ"),
("ㄙ", "s"),
("ㄚ", "a"),
("ㄛ", "o"),
("ㄜ", "ə"),
("ㄝ", "e"),
("ㄞ", "ai"),
("ㄟ", "ei"),
("ㄠ", "au"),
("ㄡ", "ou"),
("ㄧㄢ", "yeNN"),
("ㄢ", "aNN"),
("ㄧㄣ", "iNN"),
("ㄣ", "əNN"),
("ㄤ", "aNg"),
("ㄧㄥ", "iNg"),
("ㄨㄥ", "uNg"),
("ㄩㄥ", "yuNg"),
("ㄥ", "əNg"),
("ㄦ", "əɻ"),
("ㄧ", "i"),
("ㄨ", "u"),
("ㄩ", "ɥ"),
("ˉ", "→"),
("ˊ", "↑"),
("ˇ", "↓↑"),
("ˋ", "↓"),
("˙", ""),
("，", ","),
("。", "."),
("！", "!"),
("？", "?"),
("—", "-"),
]
]
# List of (romaji, ipa) pairs:
_romaji_to_ipa = [
(re.compile("%s" % x[0], re.IGNORECASE), x[1])
for x in [
("ʃy", "ʃ"),
("ʧʰy", "ʧʰ"),
("ʧ⁼y", "ʧ⁼"),
("NN", "n"),
("Ng", "ŋ"),
("y", "j"),
("h", "x"),
]
]
# List of (bopomofo, ipa) pairs:
_bopomofo_to_ipa = [
(re.compile("%s" % x[0]), x[1])
for x in [
("ㄅㄛ", "p⁼wo"),
("ㄆㄛ", "pʰwo"),
("ㄇㄛ", "mwo"),
("ㄈㄛ", "fwo"),
("ㄧㄢ", "jɛn"),
("ㄩㄢ", "ɥæn"),
("ㄧㄣ", "in"),
("ㄩㄣ", "ɥn"),
("ㄧㄥ", "iŋ"),
("ㄨㄥ", "ʊŋ"),
("ㄩㄥ", "jʊŋ"),
# Add
("ㄧㄚ", "ia"),
("ㄧㄝ", "iɛ"),
("ㄧㄠ", "iɑʊ"),
("ㄧㄡ", "ioʊ"),
("ㄧㄤ", "iɑŋ"),
("ㄨㄚ", "ua"),
("ㄨㄛ", "uo"),
("ㄨㄞ", "uaɪ"),
("ㄨㄟ", "ueɪ"),
("ㄨㄢ", "uan"),
("ㄨㄣ", "uən"),
("ㄨㄤ", "uɑŋ"),
("ㄩㄝ", "ɥɛ"),
# End
("ㄅ", "p⁼"),
("ㄆ", "pʰ"),
("ㄇ", "m"),
("ㄈ", "f"),
("ㄉ", "t⁼"),
("ㄊ", "tʰ"),
("ㄋ", "n"),
("ㄌ", "l"),
("ㄍ", "k⁼"),
("ㄎ", "kʰ"),
("ㄏ", "x"),
("ㄐ", "tʃ⁼"),
("ㄑ", "tʃʰ"),
("ㄒ", "ʃ"),
("ㄓ", "ts`⁼"),
("ㄔ", "ts`ʰ"),
("ㄕ", "s`"),
("ㄖ", "ɹ`"),
("ㄗ", "ts⁼"),
("ㄘ", "tsʰ"),
("ㄙ", "s"),
("ㄚ", "a"),
("ㄛ", "o"),
("ㄜ", "ə"),
("ㄝ", "ɛ"),
("ㄞ", "aɪ"),
("ㄟ", "eɪ"),
("ㄠ", "ɑʊ"),
("ㄡ", "oʊ"),
("ㄢ", "an"),
("ㄣ", "ən"),
("ㄤ", "ɑŋ"),
("ㄥ", "əŋ"),
("ㄦ", "əɻ"),
("ㄧ", "i"),
("ㄨ", "u"),
("ㄩ", "ɥ"),
("ˉ", "→"),
("ˊ", "↑"),
("ˇ", "↓↑"),
("ˋ", "↓"),
("˙", ""),
("，", ","),
("。", "."),
("！", "!"),
("？", "?"),
("—", "-"),
]
]
# Convert numbers to Chinese pronunciation
def number_to_chinese(text):
numbers = re.findall(r"\d+(?:\.?\d+)?", text)
for number in numbers:
text = text.replace(number, cn2an.an2cn(number), 1)
return text
# Word Segmentation, and convert Chinese pronunciation to pinyin (bopomofo)
def chinese_to_bopomofo(text):
from pypinyin import lazy_pinyin, BOPOMOFO
text = text.replace("、", "，").replace("；", "，").replace("：", "，")
words = jieba.lcut(text, cut_all=False)
text = ""
for word in words:
bopomofos = lazy_pinyin(word, BOPOMOFO)
if not re.search("[\u4e00-\u9fff]", word):
text += word
continue
for i in range(len(bopomofos)):
bopomofos[i] = re.sub(r"([\u3105-\u3129])$", r"\1ˉ", bopomofos[i])
if text != "":
text += " "
text += "".join(bopomofos)
return text
# Convert latin pronunciation to pinyin (bopomofo)
def latin_to_bopomofo(text):
for regex, replacement in _latin_to_bopomofo:
text = re.sub(regex, replacement, text)
return text
# Convert pinyin (bopomofo) to Romaji (not used)
def bopomofo_to_romaji(text):
for regex, replacement in _bopomofo_to_romaji:
text = re.sub(regex, replacement, text)
return text
# Convert pinyin (bopomofo) to IPA
def bopomofo_to_ipa(text):
for regex, replacement in _bopomofo_to_ipa:
text = re.sub(regex, replacement, text)
return text
# Convert Chinese to Romaji (not used)
def chinese_to_romaji(text):
text = number_to_chinese(text)
text = chinese_to_bopomofo(text)
text = latin_to_bopomofo(text)
text = bopomofo_to_romaji(text)
text = re.sub("i([aoe])", r"y\1", text)
text = re.sub("u([aoəe])", r"w\1", text)
text = re.sub("([ʦsɹ]`[⁼ʰ]?)([→↓↑ ]+|$)", r"\1ɹ`\2", text).replace("ɻ", "ɹ`")
text = re.sub("([ʦs][⁼ʰ]?)([→↓↑ ]+|$)", r"\1ɹ\2", text)
return text
# Convert Chinese to IPA
def chinese_to_ipa(text):
text = number_to_chinese(text)
text = chinese_to_bopomofo(text)
text = latin_to_bopomofo(text)
text = bopomofo_to_ipa(text)
text = re.sub("i([aoe])", r"j\1", text)
text = re.sub("u([aoəe])", r"w\1", text)
text = re.sub("([sɹ]`[⁼ʰ]?)([→↓↑ ]+|$)", r"\1ɹ`\2", text).replace("ɻ", "ɹ`")
text = re.sub("([s][⁼ʰ]?)([→↓↑ ]+|$)", r"\1ɹ\2", text)
return text
|