1512 Commits (7cddfd27f761e47e50d31d7a68f0394b76958143)

 

All Branches   

Search

Author	SHA1	Message	Date
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).	9 years ago
dangqingqing	7c85e0fdb5	Support variable input batch and sortagrad.	9 years ago
yangyaming	d2e467385d	Add loading model function for train.py.	9 years ago
Xinghai Sun	730d5c4dd3	Update DS2 README.md and fix bug in librispeech.py	9 years ago
Xinghai Sun	2a83486500	Refactor decoder interfaces and add ./data directory.	9 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.	9 years ago
Xinghai Sun	e6a349992b	Refactor data utils into a class and add feature normalization.	10 years ago
Xinghai Sun	9c3cd3c704	Update some parameters and comments.	10 years ago
Xinghai Sun	0babc5c4d7	Add function docs.	10 years ago
Xinghai Sun	70a343a499	Add infererence and add SortaGrad for only first pass.	10 years ago
Xinghai Sun	3fc94427db	Add librispeech dataset, audio data provider and simplfied DeepSpeech2 model configuration. ... Bug exists when run training.	10 years ago
Xinghai Sun	d59b8ca97e	Add deep_speech_2 folder.	10 years ago