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/_utils.py

80 lines
2.4 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
from pypinyin.standard import convert_finals
from pypinyin.style._constants import _INITIALS
from pypinyin.style._constants import _INITIALS_NOT_STRICT
from pypinyin.style._constants import PHONETIC_SYMBOL_DICT
from pypinyin.style._constants import PHONETIC_SYMBOL_DICT_KEY_LENGTH_NOT_ONE
from pypinyin.style._constants import RE_NUMBER
from pypinyin.style._constants import RE_PHONETIC_SYMBOL
from typing import Text
def get_initials(pinyin: Text, strict: bool) -> Text:
"""获取单个拼音中的声母.
:param pinyin: 单个拼音
:type pinyin: unicode
:param strict: 是否严格遵照汉语拼音方案来处理声母和韵母
:return: 声母
:rtype: unicode
"""
if strict:
_initials = _INITIALS
else:
_initials = _INITIALS_NOT_STRICT
for i in _initials:
if pinyin.startswith(i):
return i
return ''
def get_finals(pinyin: Text, strict: bool) -> Text:
"""获取单个拼音中的韵母.
:param pinyin: 单个拼音
:type pinyin: unicode
:param strict: 是否严格遵照汉语拼音方案来处理声母和韵母
:return: 韵母
:rtype: unicode
"""
if strict:
pinyin = convert_finals(pinyin)
initials = get_initials(pinyin, strict=strict) or ''
# 没有声母,整个都是韵母
if not initials:
return pinyin
# 按声母分割,剩下的就是韵母
return ''.join(pinyin.split(initials, 1))
def has_finals(pinyin: Text) -> bool:
"""判断是否有韵母"""
# 鼻音: 'm̄', 'ḿ', 'm̀', 'ń', 'ň', 'ǹ ' 没有韵母
for symbol in ['', 'ḿ', '', 'ń', 'ň', 'ǹ', 'ê̄', 'ế', 'ê̌', '']:
if symbol in pinyin:
return False
return True
def replace_symbol_to_number(pinyin: Text) -> Text:
"""把声调替换为数字"""
def _replace(match):
symbol = match.group(0) # 带声调的字符
# 返回使用数字标识声调的字符
return PHONETIC_SYMBOL_DICT[symbol]
# 替换拼音中的带声调字符
value = RE_PHONETIC_SYMBOL.sub(_replace, pinyin)
for symbol, to in PHONETIC_SYMBOL_DICT_KEY_LENGTH_NOT_ONE.items():
value = value.replace(symbol, to)
return value
def replace_symbol_to_no_symbol(pinyin: Text) -> Text:
"""把带声调字符替换为没有声调的字符"""
value = replace_symbol_to_number(pinyin)
return RE_NUMBER.sub('', value)