dangqingqing
9c27b1d14e
add more comments and update train.py
8 years ago
dangqingqing
bf73540067
Merge branch 'develop' of https://github.com/PaddlePaddle/models into ds2
8 years ago
dangqingqing
c25c62b8f9
refine audio_data_utils.py
8 years ago
Yibing Liu
bb34e90398
correct typos in annotations
8 years ago
Yibing Liu
ae83a25aff
add beam search decoder using multiprocesses
8 years ago
Yibing Liu
453f038df9
optimize the efficiency of beam search
8 years ago
Yibing Liu
9fda521ee3
improve external scorer
8 years ago
Yibing Liu
b046e651e7
tiny modify to pass CI
8 years ago
Yibing Liu
44efbed798
rename variables in decoder
8 years ago
Yibing Liu
21ff590e6d
modify language model scoring
8 years ago
Yibing Liu
ac370eca85
add annotations
8 years ago
Yibing Liu
51f35a5372
code clean & add external scorer
8 years ago
Yibing Liu
dedbfb2654
enable ctc beam search decoder
8 years ago
Yibing Liu
cfe9d22866
update annotations
8 years ago
Yibing Liu
c943ca79ac
mv ctc_beam_search_decoder into deep_speech_2/
8 years ago
Xinghai Sun
e016778e20
Merge pull request #78 from xinghai-sun/ds2_libri
...
Update librispeech.py for DeepSpeech2.
8 years ago
Xinghai Sun
06e9f71389
Remove manifest's line number check from librispeech.py and update README.md.
8 years ago
yangyaming
3f63e069e0
Fix typos and follow comments.
8 years ago
yangyaming
cc2a4d4e3d
Add error rate calculation script.
8 years ago
yangyaming
f49eab5fec
Change assert to exception raising.
8 years ago
Xinghai Sun
d3eeb7fd76
Refine librispeech.py for DeepSpeech2.
...
Summary:
1. Add manifest line check.
2. Avoid re-unpacking if unpacked data already exists.
3. Add full_download (download all 7 sub-datasets of LibriSpeech).
8 years ago
dangqingqing
7c85e0fdb5
Support variable input batch and sortagrad.
8 years ago
yangyaming
d2e467385d
Add loading model function for train.py.
8 years ago
Xinghai Sun
730d5c4dd3
Update DS2 README.md and fix bug in librispeech.py
8 years ago
Xinghai Sun
2a83486500
Refactor decoder interfaces and add ./data directory.
8 years ago
Xinghai Sun
8313895e85
1. Fix incorrect decoder result printing.
...
2. Fix incorrect batch-norm usage in RNN.
3. Fix overlapping train/dev/test manfests.
4. Update README.md and requirements.txt.
5. Expose more arguments to users in argparser.
6. Update all other details.
8 years ago
Xinghai Sun
e6a349992b
Refactor data utils into a class and add feature normalization.
8 years ago
Xinghai Sun
9c3cd3c704
Update some parameters and comments.
8 years ago
Xinghai Sun
0babc5c4d7
Add function docs.
8 years ago
Xinghai Sun
70a343a499
Add infererence and add SortaGrad for only first pass.
8 years ago
Xinghai Sun
3fc94427db
Add librispeech dataset, audio data provider and simplfied DeepSpeech2 model configuration.
...
Bug exists when run training.
8 years ago
Xinghai Sun
d59b8ca97e
Add deep_speech_2 folder.
8 years ago