import os import sys import re from pypinyin import lazy_pinyin, BOPOMOFO import jieba import cn2an import logging logging.getLogger('jieba').setLevel(logging.WARNING) jieba.set_dictionary(os.path.dirname(os.path.realpath(sys.argv[0])) + '/jieba/dict.txt') jieba.initialize() # 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'), ('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'), ('ㄧㄢ', 'jɛn'), ('ㄩㄢ', 'ɥæn'), ('ㄢ', 'an'), ('ㄧㄣ', 'in'), ('ㄩㄣ', 'ɥn'), ('ㄣ', 'ən'), ('ㄤ', 'ɑŋ'), ('ㄧㄥ', 'iŋ'), ('ㄨㄥ', 'ʊŋ'), ('ㄩㄥ', 'jʊŋ'), ('ㄥ', 'əŋ'), ('ㄦ', 'əɻ'), ('ㄧ', 'i'), ('ㄨ', 'u'), ('ㄩ', 'ɥ'), ('ˉ', '→'), ('ˊ', '↑'), ('ˇ', '↓↑'), ('ˋ', '↓'), ('˙', ''), (',', ','), ('。', '.'), ('!', '!'), ('?', '?'), ('—', '-') ]] # List of (bopomofo, ipa2) pairs: _bopomofo_to_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [ ('ㄅㄛ', 'pwo'), ('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', 'tɕ'), ('ㄑ', 'tɕʰ'), ('ㄒ', 'ɕ'), ('ㄓ', 'tʂ'), ('ㄔ', 'tʂʰ'), ('ㄕ', 'ʂ'), ('ㄖ', 'ɻ'), ('ㄗ', 'ts'), ('ㄘ', 'tsʰ'), ('ㄙ', 's'), ('ㄚ', 'a'), ('ㄛ', 'o'), ('ㄜ', 'ɤ'), ('ㄝ', 'ɛ'), ('ㄞ', 'aɪ'), ('ㄟ', 'eɪ'), ('ㄠ', 'ɑʊ'), ('ㄡ', 'oʊ'), ('ㄧㄢ', 'jɛn'), ('ㄩㄢ', 'yæn'), ('ㄢ', 'an'), ('ㄧㄣ', 'in'), ('ㄩㄣ', 'yn'), ('ㄣ', 'ən'), ('ㄤ', 'ɑŋ'), ('ㄧㄥ', 'iŋ'), ('ㄨㄥ', 'ʊŋ'), ('ㄩㄥ', 'jʊŋ'), ('ㄥ', 'ɤŋ'), ('ㄦ', 'əɻ'), ('ㄧ', 'i'), ('ㄨ', 'u'), ('ㄩ', 'y'), ('ˉ', '˥'), ('ˊ', '˧˥'), ('ˇ', '˨˩˦'), ('ˋ', '˥˩'), ('˙', ''), (',', ','), ('。', '.'), ('!', '!'), ('?', '?'), ('—', '-') ]] _symbols_to_chinese = [(re.compile(f'{x[0]}'), x[1]) for x in [ ('([0-9]+(?:\.?[0-9]+)?)%', r'百分之\1'), ('([0-9]+)/([0-9]+)', r'\2分之\1'), ('\+', r'加'), ('([0-9]+)-([0-9]+)', r'\1减\2'), ('×', r'乘以'), ('([0-9]+)x([0-9]+)', r'\1乘以\2'), ('([0-9]+)\*([0-9]+)', r'\1乘以\2'), ('÷', r'除以'), ('=', r'等于'), ('≠', r'不等于'), ]] def symbols_to_chinese(text): for regex, replacement in _symbols_to_chinese: text = re.sub(regex, replacement, text) return text def number_to_chinese(text): numbers = re.findall(r'[0-9]+(?:\.?[0-9]+)?', text) for number in numbers: text = text.replace(number, cn2an.an2cn(number), 1) return text def number_transform_to_chinese(text): text = cn2an.transform(text, "an2cn") return text def chinese_to_bopomofo(text): 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])$', r'\1ˉ', bopomofos[i]) if text != '': text += ' ' text += ''.join(bopomofos) return text def latin_to_bopomofo(text): for regex, replacement in _latin_to_bopomofo: text = re.sub(regex, replacement, text) return text def bopomofo_to_romaji(text): for regex, replacement in _bopomofo_to_romaji: text = re.sub(regex, replacement, text) return text def bopomofo_to_ipa(text): for regex, replacement in _bopomofo_to_ipa: text = re.sub(regex, replacement, text) return text def bopomofo_to_ipa2(text): for regex, replacement in _bopomofo_to_ipa2: text = re.sub(regex, replacement, text) return text def chinese_to_romaji(text): text = symbols_to_chinese(text) text = number_transform_to_chinese(text) text = chinese_to_bopomofo(text) text = latin_to_bopomofo(text) text = bopomofo_to_romaji(text) text = re.sub('i([aoe])', r'y\1', text) text = re.sub('u([aoəe])', r'w\1', text) text = re.sub('([ʦsɹ]`[⁼ʰ]?)([→↓↑ ]+|$)', r'\1ɹ`\2', text).replace('ɻ', 'ɹ`') text = re.sub('([ʦs][⁼ʰ]?)([→↓↑ ]+|$)', r'\1ɹ\2', text) return text def chinese_to_lazy_ipa(text): text = chinese_to_romaji(text) for regex, replacement in _romaji_to_ipa: text = re.sub(regex, replacement, text) return text def chinese_to_ipa(text): text = symbols_to_chinese(text) text = number_transform_to_chinese(text) text = chinese_to_bopomofo(text) text = latin_to_bopomofo(text) text = bopomofo_to_ipa(text) text = re.sub('i([aoe])', r'j\1', text) text = re.sub('u([aoəe])', r'w\1', text) text = re.sub('([sɹ]`[⁼ʰ]?)([→↓↑ ]+|$)', r'\1ɹ`\2', text).replace('ɻ', 'ɹ`') text = re.sub('([s][⁼ʰ]?)([→↓↑ ]+|$)', r'\1ɹ\2', text) return text def chinese_to_ipa2(text): text = symbols_to_chinese(text) text = number_transform_to_chinese(text) text = chinese_to_bopomofo(text) text = latin_to_bopomofo(text) text = bopomofo_to_ipa2(text) text = re.sub(r'i([aoe])', r'j\1', text) text = re.sub(r'u([aoəe])', r'w\1', text) text = re.sub(r'([ʂɹ]ʰ?)([˩˨˧˦˥ ]+|$)', r'\1ʅ\2', text) text = re.sub(r'(sʰ?)([˩˨˧˦˥ ]+|$)', r'\1ɿ\2', text) return text def VITS_PinYin_model(): import torch import config from vits_pinyin import VITS_PinYin device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # pinyin tts_front = VITS_PinYin(f"{config.ABS_PATH}/bert", device) return tts_front