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/tests/error_rate_test.py

125 lines
4.9 KiB

3 years ago
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
7 years ago
"""Test error rate."""
7 years ago
import unittest
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
Support paddle 2.x (#538) * 2.x model * model test pass * fix data * fix soundfile with flac support * one thread dataloader test pass * export feasture size add trainer and utils add setup model and dataloader update travis using Bionic dist * add venv; test under venv * fix unittest; train and valid * add train and config * add config and train script * fix ctc cuda memcopy error * fix imports * fix train valid log * fix dataset batch shuffle shift start from 1 fix rank_zero_only decreator error close tensorboard when train over add decoding config and code * test process can run * test with decoding * test and infer with decoding * fix infer * fix ctc loss lr schedule sortagrad logger * aishell egs * refactor train add aishell egs * fix dataset batch shuffle and add batch sampler log print model parameter * fix model and ctc * sequence_mask make all inputs zeros, which cause grad be zero, this is a bug of LessThanOp add grad clip by global norm add model train test notebook * ctc loss remove run prefix using ord value as text id * using unk when training compute_loss need text ids ord id using in test mode, which compute wer/cer * fix tester * add lr_deacy refactor code * fix tools * fix ci add tune fix gru model bugs add dataset and model test * fix decoding * refactor repo fix decoding * fix musan and rir dataset * refactor io, loss, conv, rnn, gradclip, model, utils * fix ci and import * refactor model add export jit model * add deploy bin and test it * rm uselss egs * add layer tools * refactor socket server new model from pretrain * remve useless * fix instability loss and grad nan or inf for librispeech training * fix sampler * fix libri train.sh * fix doc * add license on cpp * fix doc * fix libri script * fix install * clip 5 wer 7.39, clip 400 wer 7.54, 1.8 clip 400 baseline 7.49
3 years ago
from deepspeech.utils import error_rate
7 years ago
class TestParse(unittest.TestCase):
7 years ago
def test_wer_1(self):
7 years ago
ref = 'i UM the PHONE IS i LEFT THE portable PHONE UPSTAIRS last night'
hyp = 'i GOT IT TO the FULLEST i LOVE TO portable FROM OF STORES last '\
'night'
7 years ago
word_error_rate = error_rate.wer(ref, hyp)
self.assertTrue(abs(word_error_rate - 0.769230769231) < 1e-6)
7 years ago
def test_wer_2(self):
ref = 'as any in england i would say said gamewell proudly that is '\
'in his day'
hyp = 'as any in england i would say said came well proudly that is '\
'in his day'
word_error_rate = error_rate.wer(ref, hyp)
self.assertTrue(abs(word_error_rate - 0.1333333) < 1e-6)
def test_wer_3(self):
ref = 'the lieutenant governor lilburn w boggs afterward governor '\
'was a pronounced mormon hater and throughout the period of '\
'the troubles he manifested sympathy with the persecutors'
hyp = 'the lieutenant governor little bit how bags afterward '\
'governor was a pronounced warman hater and throughout the '\
'period of th troubles he manifests sympathy with the '\
'persecutors'
word_error_rate = error_rate.wer(ref, hyp)
self.assertTrue(abs(word_error_rate - 0.2692307692) < 1e-6)
def test_wer_4(self):
ref = 'the wood flamed up splendidly under the large brewing copper '\
'and it sighed so deeply'
hyp = 'the wood flame do splendidly under the large brewing copper '\
'and its side so deeply'
word_error_rate = error_rate.wer(ref, hyp)
self.assertTrue(abs(word_error_rate - 0.2666666667) < 1e-6)
def test_wer_5(self):
ref = 'all the morning they trudged up the mountain path and at noon '\
'unc and ojo sat on a fallen tree trunk and ate the last of '\
'the bread which the old munchkin had placed in his pocket'
hyp = 'all the morning they trudged up the mountain path and at noon '\
'unc in ojo sat on a fallen tree trunk and ate the last of '\
'the bread which the old munchkin had placed in his pocket'
word_error_rate = error_rate.wer(ref, hyp)
self.assertTrue(abs(word_error_rate - 0.027027027) < 1e-6)
def test_wer_6(self):
7 years ago
ref = 'i UM the PHONE IS i LEFT THE portable PHONE UPSTAIRS last night'
word_error_rate = error_rate.wer(ref, ref)
self.assertEqual(word_error_rate, 0.0)
def test_wer_7(self):
7 years ago
ref = ' '
hyp = 'Hypothesis sentence'
7 years ago
with self.assertRaises(ValueError):
7 years ago
word_error_rate = error_rate.wer(ref, hyp)
def test_cer_1(self):
7 years ago
ref = 'werewolf'
hyp = 'weae wolf'
char_error_rate = error_rate.cer(ref, hyp)
self.assertTrue(abs(char_error_rate - 0.25) < 1e-6)
7 years ago
def test_cer_2(self):
ref = 'werewolf'
hyp = 'weae wolf'
char_error_rate = error_rate.cer(ref, hyp, remove_space=True)
self.assertTrue(abs(char_error_rate - 0.125) < 1e-6)
def test_cer_3(self):
ref = 'were wolf'
hyp = 'were wolf'
char_error_rate = error_rate.cer(ref, hyp)
self.assertTrue(abs(char_error_rate - 0.0) < 1e-6)
def test_cer_4(self):
7 years ago
ref = 'werewolf'
char_error_rate = error_rate.cer(ref, ref)
self.assertEqual(char_error_rate, 0.0)
def test_cer_5(self):
7 years ago
ref = u'我是中国人'
hyp = u'我是 美洲人'
char_error_rate = error_rate.cer(ref, hyp)
self.assertTrue(abs(char_error_rate - 0.6) < 1e-6)
def test_cer_6(self):
ref = u'我 是 中 国 人'
hyp = u'我 是 美 洲 人'
char_error_rate = error_rate.cer(ref, hyp, remove_space=True)
self.assertTrue(abs(char_error_rate - 0.4) < 1e-6)
def test_cer_7(self):
7 years ago
ref = u'我是中国人'
char_error_rate = error_rate.cer(ref, ref)
self.assertFalse(char_error_rate, 0.0)
def test_cer_8(self):
7 years ago
ref = ''
hyp = 'Hypothesis'
7 years ago
with self.assertRaises(ValueError):
7 years ago
char_error_rate = error_rate.cer(ref, hyp)
7 years ago
if __name__ == '__main__':
unittest.main()