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/tests/test_converter.py

84 lines
3.2 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.constants import Style
from pypinyin.converter import DefaultConverter
def test_pre_convert_style_return_value():
class A(DefaultConverter):
def pre_convert_style(self, han, orig_pinyin, style, strict, **kwargs):
return 'test'
han = '测试'
assert DefaultConverter().convert(han, Style.TONE2, False, 'ignore',
True) == [['ce4'], ['shi4']]
assert A().convert(han, Style.TONE2, False, 'ignore', True) == [['test'],
['test']]
def test_post_convert_style_return_value():
class A(DefaultConverter):
def post_convert_style(self, han, orig_pinyin, converted_pinyin, style,
strict, **kwargs):
return 'test'
han = '测试'
assert DefaultConverter().convert(han, Style.TONE2, False, 'ignore',
True) == [['ce4'], ['shi4']]
assert A().convert(han, Style.TONE2, False, 'ignore', True) == [['test'],
['test']]
def test_pre_handle_nopinyin_return_value():
class A(DefaultConverter):
def pre_handle_nopinyin(self, chars, style, heteronym, errors, strict,
**kwargs):
return 'abc'
han = 'test'
assert DefaultConverter().convert(han, Style.TONE2, False, 'default',
True) == [['test']]
assert A().convert(han, Style.TONE2, False, 'default', True) == [['abc']]
def test_post_handle_nopinyin_return_value():
class A(DefaultConverter):
def post_handle_nopinyin(self, chars, style, heteronym, errors, strict,
pinyin, **kwargs):
return 'abc'
han = 'test'
assert DefaultConverter().convert(han, Style.TONE2, False, 'default',
True) == [['test']]
assert A().convert(han, Style.TONE2, False, 'default', True) == [['abc']]
def test_post_pinyin_return_value_single_pinyin():
class A(DefaultConverter):
def post_pinyin(self, han, heteronym, pinyin, **kwargs):
return {
'': [['zhāo']],
'': [['yáng']],
'测试': [['zhāo'], ['yáng']],
}[han]
han = '测试'
assert DefaultConverter().convert(han, Style.TONE3, False, 'ignore',
True) == [['ce4'], ['shi4']]
assert A().convert(han, Style.TONE3, False, 'ignore', True) == [['zhao1'],
['yang2']]
def test_post_pinyin_return_value_phrase_pinyin():
class A(DefaultConverter):
def post_pinyin(self, han, heteronym, pinyin, **kwargs):
return {
'': [['zhāo']],
'': [['yáng']],
'北京': [['zhāo'], ['yáng']],
}[han]
han = '北京'
assert DefaultConverter().convert(han, Style.TONE3, False, 'ignore',
True) == [['bei3'], ['jing1']]
assert A().convert(han, Style.TONE3, False, 'ignore', True) == [['zhao1'],
['yang2']]