Yibing Liu
8ba98cb518
fix decoders' unittest
7 years ago
Yibing Liu
26510f74a6
refine ctc_beam_search_decoder
7 years ago
Yibing Liu
237df23e7e
Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev
7 years ago
Xinghai Sun
0dadd14600
Patch for adding missing shift_perturb.py in last commmit (pull request #114 ).
7 years ago
Yibing Liu
7324d41e4a
Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev
7 years ago
Xinghai Sun
cdd52ac270
Fix a missing abs bug for DS2 AudioSegment.
7 years ago
Xinghai Sun
13f708739b
Improve audio featurizer and add shift augmentor.
...
1. Improve audio featurizer.
2. Add shift augmentor.
3. Update default argument to be the current best seggestion.
4. Add checkpoints with pass id.
7 years ago
Yibing Liu
8033845615
add unit test for decoders
7 years ago
Yibing Liu
f20c6d643f
Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev
7 years ago
Xinghai Sun
d104eccf67
Update the default num_threads for DS2 data generator.
7 years ago
Xinghai Sun
1d8cc4a5a9
Add multi-threading support for DS2 data generator.
7 years ago
Yibing Liu
0729abe02e
tiny adjust
7 years ago
Yibing Liu
d8089315f4
Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev
7 years ago
yangyaming
a5dcd23bf2
Follow comments.
7 years ago
yangyaming
d35b747175
Fix ci following:
...
1. Unify the dependency installation process in setup.sh.
2. Change the version of package scipy from 0.13.0b1 to 0.13.1
7 years ago
Yibing Liu
b2cf96cc46
adapt to the new data provider
7 years ago
Xinghai Sun
d1f5123bcf
Merge pull request #99 from PaddlePaddle/new_augmentation_2
...
Add some audio transformation methods to AudioSegment and SpeechSegment class.
7 years ago
yangyaming
def66a3223
Follow comments.
7 years ago
chrisxu2016
ddb2bdc190
add audio file
7 years ago
chrisxu2016
25ce7ebe7b
add audio file
7 years ago
Yibing Liu
36743d3689
add scoring last word in beam search
7 years ago
chrisxu2016
21161b0165
add audio file
7 years ago
chrisxu2016
107f8b89ae
add audio augmentation
7 years ago
Yibing Liu
ff01d048d3
final refining on old data provider: enable pruning & add evaluation & code cleanup
7 years ago
chrisxu2016
b8341da63d
add audio augmentation
7 years ago
yangyaming
26eb54eb37
Follow comments.
7 years ago
yangyaming
86eeb52c06
Merge branch 'develop' of https://github.com/PaddlePaddle/models into fix-81
7 years ago
chrisxu2016
5ca270d30a
add audio file
7 years ago
chrisxu2016
d1ee10be10
modify audio and speech
7 years ago
chrisxu2016
d66d740ea0
add audio part
7 years ago
Xinghai Sun
ed5f04afb8
Add shuffle type of instance_shuffle and batch_shuffle_clipped.
7 years ago
chrisxu2016
65e34c535b
add augmentation
7 years ago
Xinghai Sun
04a225ae4f
Enable min_batch_num in train.py and update train info print.
7 years ago
yangyaming
f85f8558cf
Add unittest.
7 years ago
yangyaming
397b2fc288
Merge branch 'develop' of https://github.com/PaddlePaddle/models into fix-81
7 years ago
Xinghai Sun
1cef98f210
Update README.md for DS2.
7 years ago
Xinghai Sun
b07ee84a1d
Add function, class and module docs for data parts in DS2.
7 years ago
Yibing Liu
a633eb9cc6
change two arguments
7 years ago
Yibing Liu
7db13ca9db
enable lm in multiprocessing decoder & add script for params tuning
7 years ago
yangyaming
bc3224eb14
Follow comments.
7 years ago
Xinghai Sun
cd3617aeb4
Refactor whole data preprocessor for DS2 (re-design classes, re-organize dir, add augmentaion interfaces etc.).
...
1. Refactor data preprocessor with new added class AudioSegment, SpeechSegment, TextFeaturizer, AudioFeaturizer, SpeechFeaturizer.
2. Add data augmentation interfaces and class AugmentorBase, AugmentationPipeline, VolumnPerturbAugmentor etc..
3. Seperate normalizer's mean and std computing from training, by adding FeatureNormalizer and a seperate tool compute_mean_std.py.
4. Re-organize directory.
7 years ago
dangqingqing
9c27b1d14e
add more comments and update train.py
7 years ago
dangqingqing
bf73540067
Merge branch 'develop' of https://github.com/PaddlePaddle/models into ds2
7 years ago
dangqingqing
c25c62b8f9
refine audio_data_utils.py
7 years ago
Yibing Liu
bb34e90398
correct typos in annotations
7 years ago
Yibing Liu
ae83a25aff
add beam search decoder using multiprocesses
7 years ago
Yibing Liu
453f038df9
optimize the efficiency of beam search
7 years ago
Yibing Liu
9fda521ee3
improve external scorer
7 years ago
Yibing Liu
b046e651e7
tiny modify to pass CI
7 years ago
Yibing Liu
44efbed798
rename variables in decoder
7 years ago