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/deepspeech/decoders/tests/test_decoders.py

101 lines
3.9 KiB

4 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.
"""Test decoders."""
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
4 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
4 years ago
from deepspeech.decoders import decoders_deprecated as decoder
class TestDecoders(unittest.TestCase):
def setUp(self):
self.vocab_list = ["\'", ' ', 'a', 'b', 'c', 'd']
self.beam_size = 20
self.probs_seq1 = [[
0.06390443, 0.21124858, 0.27323887, 0.06870235, 0.0361254,
0.18184413, 0.16493624
], [
0.03309247, 0.22866108, 0.24390638, 0.09699597, 0.31895462,
0.0094893, 0.06890021
], [
0.218104, 0.19992557, 0.18245131, 0.08503348, 0.14903535,
0.08424043, 0.08120984
], [
0.12094152, 0.19162472, 0.01473646, 0.28045061, 0.24246305,
0.05206269, 0.09772094
], [
0.1333387, 0.00550838, 0.00301669, 0.21745861, 0.20803985,
0.41317442, 0.01946335
], [
0.16468227, 0.1980699, 0.1906545, 0.18963251, 0.19860937,
0.04377724, 0.01457421
]]
self.probs_seq2 = [[
0.08034842, 0.22671944, 0.05799633, 0.36814645, 0.11307441,
0.04468023, 0.10903471
], [
0.09742457, 0.12959763, 0.09435383, 0.21889204, 0.15113123,
0.10219457, 0.20640612
], [
0.45033529, 0.09091417, 0.15333208, 0.07939558, 0.08649316,
0.12298585, 0.01654384
], [
0.02512238, 0.22079203, 0.19664364, 0.11906379, 0.07816055,
0.22538587, 0.13483174
], [
0.17928453, 0.06065261, 0.41153005, 0.1172041, 0.11880313,
0.07113197, 0.04139363
], [
0.15882358, 0.1235788, 0.23376776, 0.20510435, 0.00279306,
0.05294827, 0.22298418
]]
self.greedy_result = ["ac'bdc", "b'da"]
self.beam_search_result = ['acdc', "b'a"]
def test_greedy_decoder_1(self):
bst_result = decoder.ctc_greedy_decoder(self.probs_seq1,
self.vocab_list)
self.assertEqual(bst_result, self.greedy_result[0])
def test_greedy_decoder_2(self):
bst_result = decoder.ctc_greedy_decoder(self.probs_seq2,
self.vocab_list)
self.assertEqual(bst_result, self.greedy_result[1])
def test_beam_search_decoder_1(self):
beam_result = decoder.ctc_beam_search_decoder(
probs_seq=self.probs_seq1,
beam_size=self.beam_size,
vocabulary=self.vocab_list)
self.assertEqual(beam_result[0][1], self.beam_search_result[0])
def test_beam_search_decoder_2(self):
beam_result = decoder.ctc_beam_search_decoder(
probs_seq=self.probs_seq2,
beam_size=self.beam_size,
vocabulary=self.vocab_list)
self.assertEqual(beam_result[0][1], self.beam_search_result[1])
def test_beam_search_decoder_batch(self):
beam_results = decoder.ctc_beam_search_decoder_batch(
probs_split=[self.probs_seq1, self.probs_seq2],
beam_size=self.beam_size,
vocabulary=self.vocab_list,
num_processes=24)
self.assertEqual(beam_results[0][0][1], self.beam_search_result[0])
self.assertEqual(beam_results[1][0][1], self.beam_search_result[1])
if __name__ == '__main__':
unittest.main()