PaddleSpeech

Author	SHA1	Message	Date
dangqingqing	bf73540067	Merge branch 'develop' of https://github.com/PaddlePaddle/models into ds2	7 years ago
yangyaming	f49eab5fec	Change assert to exception raising.	7 years ago
dangqingqing	7c85e0fdb5	Support variable input batch and sortagrad.	7 years ago
yangyaming	d2e467385d	Add loading model function for train.py.	7 years ago
Xinghai Sun	2a83486500	Refactor decoder interfaces and add ./data directory.	7 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.	7 years ago
Xinghai Sun	e6a349992b	Refactor data utils into a class and add feature normalization.	7 years ago
Xinghai Sun	9c3cd3c704	Update some parameters and comments.	7 years ago
Xinghai Sun	0babc5c4d7	Add function docs.	7 years ago
Xinghai Sun	70a343a499	Add infererence and add SortaGrad for only first pass.	7 years ago
Xinghai Sun	3fc94427db	Add librispeech dataset, audio data provider and simplfied DeepSpeech2 model configuration. Bug exists when run training.	7 years ago