You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/third_party/python-pinyin/pypinyin/style/finals.py

73 lines
2.3 KiB

E2E/Streaming Transformer/Conformer ASR (#578) * add cmvn and label smoothing loss layer * add layer for transformer * add glu and conformer conv * add torch compatiable hack, mask funcs * not hack size since it exists * add test; attention * add attention, common utils, hack paddle * add audio utils * conformer batch padding mask bug fix #223 * fix typo, python infer fix rnn mem opt name error and batchnorm1d, will be available at 2.0.2 * fix ci * fix ci * add encoder * refactor egs * add decoder * refactor ctc, add ctc align, refactor ckpt, add warmup lr scheduler, cmvn utils * refactor docs * add fix * fix readme * fix bugs, refactor collator, add pad_sequence, fix ckpt bugs * fix docstring * refactor data feed order * add u2 model * refactor cmvn, test * add utils * add u2 config * fix bugs * fix bugs * fix autograd maybe has problem when using inplace operation * refactor data, build vocab; add format data * fix text featurizer * refactor build vocab * add fbank, refactor feature of speech * refactor audio feat * refactor data preprare * refactor data * model init from config * add u2 bins * flake8 * can train * fix bugs, add coverage, add scripts * test can run * fix data * speed perturb with sox * add spec aug * fix for train * fix train logitc * fix logger * log valid loss, time dataset process * using np for speed perturb, remove some debug log of grad clip * fix logger * fix build vocab * fix logger name * using module logger as default * fix * fix install * reorder imports * fix board logger * fix logger * kaldi fbank and mfcc * fix cmvn and print prarams * fix add_eos_sos and cmvn * fix cmvn compute * fix logger and cmvn * fix subsampling, label smoothing loss, remove useless * add notebook test * fix log * fix tb logger * multi gpu valid * fix log * fix log * fix config * fix compute cmvn, need paddle 2.1 * add cmvn notebook * fix layer tools * fix compute cmvn * add rtf * fix decoding * fix layer tools * fix log, add avg script * more avg and test info * fix dataset pickle problem; using 2.1 paddle; num_workers can > 0; ckpt save in exp dir;fix setup.sh; * add vimrc * refactor tiny script, add transformer and stream conf * spm demo; librisppech scripts and confs * fix log * add librispeech scripts * refactor data pipe; fix conf; fix u2 default params * fix bugs * refactor aishell scripts * fix test * fix cmvn * fix s0 scripts * fix ds2 scripts and bugs * fix dev & test dataset filter * fix dataset filter * filter dev * fix ckpt path * filter test, since librispeech will cause OOM, but all test wer will be worse, since mismatch train with test * add comment * add syllable doc * fix ds2 configs * add doc * add pypinyin tools * fix decoder using blank_id=0 * mmseg with pybind11 * format code
3 years ago
"""韵母相关拼音风格:
Style.FINALS
Style.FINALS_TONE
Style.FINALS_TONE2
Style.FINALS_TONE3
"""
from typing import Text
from typing import Any
from pypinyin.constants import Style
from pypinyin.standard import convert_finals
from pypinyin.style import register
from pypinyin.style._constants import RE_TONE3
from pypinyin.style._utils import get_finals
from pypinyin.style._utils import has_finals
from pypinyin.style._utils import replace_symbol_to_no_symbol
from pypinyin.style._utils import replace_symbol_to_number
class FinalsConverter():
def to_finals(self, pinyin: Text, **kwargs: Any) -> Text:
if kwargs.get('strict'):
pinyin = convert_finals(pinyin)
has_fi = has_finals(pinyin)
# 替换声调字符为无声调字符
pinyin = replace_symbol_to_no_symbol(pinyin)
if not has_fi:
return pinyin
# 获取韵母部分
return get_finals(pinyin, strict=False)
def to_finals_tone(self, pinyin: Text, **kwargs: Any) -> Text:
if not has_finals(pinyin):
return pinyin
# 获取韵母部分
return get_finals(pinyin, strict=kwargs.get('strict'))
def to_finals_tone2(self, pinyin: Text, **kwargs: Any) -> Text:
if kwargs.get('strict'):
pinyin = convert_finals(pinyin)
has_fi = has_finals(pinyin)
# 用数字表示声调
pinyin = replace_symbol_to_number(pinyin)
if not has_fi:
return pinyin
# 获取韵母部分
return get_finals(pinyin, strict=False)
def to_finals_tone3(self, pinyin: Text, **kwargs: Any) -> Text:
if kwargs.get('strict'):
pinyin = convert_finals(pinyin)
has_fi = has_finals(pinyin)
# 用数字表示声调
pinyin = replace_symbol_to_number(pinyin)
# 将声调数字移动到最后
pinyin = RE_TONE3.sub(r'\1\3\2', pinyin)
if not has_fi:
return pinyin
# 获取韵母部分
return get_finals(pinyin, strict=False)
converter = FinalsConverter()
register(Style.FINALS, func=converter.to_finals)
register(Style.FINALS_TONE, func=converter.to_finals_tone)
register(Style.FINALS_TONE2, func=converter.to_finals_tone2)
register(Style.FINALS_TONE3, func=converter.to_finals_tone3)