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/pinyin-data/tools/improve_8105.py

89 lines
2.6 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
4 years ago
# -*- coding: utf-8 -*-
"""补充 8105 中汉字的拼音数据"""
from collections import namedtuple
import re
import sys
from pyquery import PyQuery
import requests
re_pinyin = re.compile(r'拼音:(?P<pinyin>\S+) ')
re_code = re.compile(r'统一码\w?(?P<code>\S+) ')
re_alternate = re.compile(r'异体字:\s+?(?P<alternate>\S+)')
HanziInfo = namedtuple('HanziInfo', 'pinyin code alternate')
def fetch_html(url, params):
response = requests.get(url, params=params)
return response.content
def fetch_info(hanzi):
url = 'http://www.guoxuedashi.com/zidian/so.php'
params = {
'sokeyzi': hanzi,
'kz': 1,
'submit': '',
}
html = fetch_html(url, params)
pq = PyQuery(html)
pq = PyQuery(pq('table.zui td')[1])
text = pq('tr').text()
text_alternate = pq(html)('.info_txt2')('em').text()
pinyin = ''
pinyin_match = re_pinyin.search(text)
if pinyin_match is not None:
pinyin = pinyin_match.group('pinyin')
code = re_code.search(text).group('code')
alternate = ''
alternate_match = re_alternate.search(text_alternate)
if alternate_match is not None:
alternate = alternate_match.group('alternate')
return HanziInfo(pinyin, code, alternate)
def parse_hanzi(hanzi):
info = fetch_info(hanzi)
if (not info.pinyin) and info.alternate:
alternate = fetch_info(info.alternate)
else:
alternate = ''
return HanziInfo(info.pinyin, info.code, alternate)
def main(lines):
for line in lines:
if line.startswith('# U+') and '<-' in line:
# # U+xxx ... -> U+xxx
code = line.split(':')[0].strip('# ')
# U+xxx -> xxx
code = code[2:]
info = parse_hanzi(code)
pinyin = info.pinyin
extra = ''
if (not pinyin) and info.alternate:
alternate = info.alternate
pinyin = alternate.pinyin
extra = ' => U+{0}'.format(alternate.code)
if ',' in pinyin:
first_pinyin, extra_pinyin = pinyin.split(',', 1)
pinyin = first_pinyin
extra += ' ?-> ' + extra_pinyin
if pinyin:
line = line.strip()
# # U+xxx -> U+xxx
line = line[2:]
line = line.replace('<-', pinyin)
if extra:
line += extra
yield line.strip()
if __name__ == '__main__':
args = sys.argv[1:]
input_file = args[0]
with open(input_file) as fp:
for line in main(fp):
print(line)