File size: 2,130 Bytes
6127b48 |
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 |
from typing import Dict
from TTS.tts.utils.text.japanese.phonemizer import japanese_text_to_phonemes
from TTS.tts.utils.text.phonemizers.base import BasePhonemizer
_DEF_JA_PUNCS = "ใ.,[]()?!ใฝ~ใใใใใใ"
_TRANS_TABLE = {"ใ": ","}
def trans(text):
for i, j in _TRANS_TABLE.items():
text = text.replace(i, j)
return text
class JA_JP_Phonemizer(BasePhonemizer):
"""๐ธTTS Ja-Jp phonemizer using functions in `TTS.tts.utils.text.japanese.phonemizer`
TODO: someone with JA knowledge should check this implementation
Example:
>>> from TTS.tts.utils.text.phonemizers import JA_JP_Phonemizer
>>> phonemizer = JA_JP_Phonemizer()
>>> phonemizer.phonemize("ใฉใกใใซ่กใใพใใ๏ผ", separator="|")
'd|o|c|h|i|r|a|n|i|i|k|i|m|a|s|u|k|a|?'
"""
language = "ja-jp"
def __init__(self, punctuations=_DEF_JA_PUNCS, keep_puncs=True, **kwargs): # pylint: disable=unused-argument
super().__init__(self.language, punctuations=punctuations, keep_puncs=keep_puncs)
@staticmethod
def name():
return "ja_jp_phonemizer"
def _phonemize(self, text: str, separator: str = "|") -> str:
ph = japanese_text_to_phonemes(text)
if separator is not None or separator != "":
return separator.join(ph)
return ph
def phonemize(self, text: str, separator="|") -> str:
"""Custom phonemize for JP_JA
Skip pre-post processing steps used by the other phonemizers.
"""
return self._phonemize(text, separator)
@staticmethod
def supported_languages() -> Dict:
return {"ja-jp": "Japanese (Japan)"}
def version(self) -> str:
return "0.0.1"
def is_available(self) -> bool:
return True
# if __name__ == "__main__":
# text = "ใใใฏใ้ป่ฉฑใใใใใใใฎ็งใฎๆฅๆฌ่ชใฎไพใฎใใญในใใงใใ"
# e = JA_JP_Phonemizer()
# print(e.supported_languages())
# print(e.version())
# print(e.language)
# print(e.name())
# print(e.is_available())
# print("`" + e.phonemize(text) + "`")
|