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/cyrillic.py

61 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
"""CYRILLIC 相关的几个拼音风格实现:
Style.CYRILLIC
Style.CYRILLIC_FIRST
"""
import re
from typing import Any
from typing import Text
from pypinyin.constants import Style
from pypinyin.style import register
from pypinyin.style._constants import RE_TONE3
from pypinyin.style._utils import replace_symbol_to_number
# 俄语转换表
CYRILLIC_REPLACE = (
(re.compile(r'ong'), 'ung'), (re.compile(r'([zcs])i'), '\\1U'),
(re.compile(r'([xqj])u'), '\\1v'), (re.compile(r'^wu(.?)$'), 'u\\1'),
(re.compile(r'(.+)r(.?)$'), '\\1R\\2'), (re.compile(r'^zh'), 'Cr'),
(re.compile(r'^ch'), 'C'), (re.compile(r'^j'), 'qZ'),
(re.compile(r'^z'), 'qZ'), (re.compile(r'^x'), 's'),
(re.compile(r'^sh'), 'S'), (re.compile(r'([^CSdst])uo'), '\\1o'),
(re.compile(r'^y(.*)$'), 'I\\1'), (re.compile(r'Iai'), 'AI'),
(re.compile(r'Ia'), 'A'), (re.compile(r'Ie'), 'E'),
(re.compile(r'Ii'), 'i'), (re.compile(r'Iou'), 'V'),
(re.compile(r'Iu'), 'v'), (re.compile(r'(.v)(\d?)$'), '\\1I\\2'),
(re.compile(r'Io'), 'O'), (re.compile(r'iu'), 'v'),
(re.compile(r'ie'), 'E'), (re.compile(r'hui'), 'huei'),
(re.compile(r'ui'), 'uI'), (re.compile(r'ai'), 'aI'),
(re.compile(r'ei'), 'eI'), (re.compile(r'ia'), 'A'),
(re.compile(r'(.*[^h])n([^g]?)$'), '\\1nM\\2'),
(re.compile(r'(.*[^h])ng(.?)$'), '\\1n\\2'),
(re.compile(r'^v(\d?$)'), 'vI'), )
CYRILLIC_TABLE = dict(
zip(u'abwgdEOrZiIklmnopRstufhqcCSHTMUevAV',
u'абвгдеёжзийклмнопрстуфхццчшщъьыэюяю'))
class CyrillicfoConverter():
def _pre_convert(self, pinyin: Text) -> Text:
# 用数字表示声调
pinyin = replace_symbol_to_number(pinyin)
# 将声调数字移动到最后
return RE_TONE3.sub(r'\1\3\2', pinyin)
def to_cyrillic(self, pinyin: Text, **kwargs: Any) -> Text:
pinyin = self._pre_convert(pinyin)
# 查表替换成注音
for find_re, replace in CYRILLIC_REPLACE:
pinyin = find_re.sub(replace, pinyin)
pinyin = ''.join(CYRILLIC_TABLE.get(x, x) for x in pinyin)
return pinyin
def to_cyrillic_first(self, pinyin: Text, **kwargs: Any) -> Text:
pinyin = self.to_cyrillic(pinyin, **kwargs)
return pinyin[0]
converter = CyrillicfoConverter()
register(Style.CYRILLIC, func=converter.to_cyrillic)
register(Style.CYRILLIC_FIRST, func=converter.to_cyrillic_first)