17 Commits (792129166ab9c1a5380d6a20eebd33ac7b7b9766)

Author	SHA1	Message	Date
Xinghai Sun	792129166a	Sort the config lines to make it look better.	7 years ago
Xinghai Sun	805846ce67	Reduce the config parsing codes for DS2 and make it looks cleaner.	7 years ago
Xinghai Sun	2aa4af1c29	Revert back to support input-hidden weights sharing between bi-directional RNNs. ... 1. Add options to enable and disable RNN weights sharing. 2. Set rnn_layer_size to 2048 by default. 3. Revert back the striding steps of 1st conv layer from 2 to 3. 4. Revert back to BRelu. Above follows DS2 papers.	7 years ago
Xinghai Sun	177af05953	Fix a bug in use_gru argument parsing.	7 years ago
Xinghai Sun	5a63275845	Add GRU support.	7 years ago
yangyaming	4b3f768df7	Simplify description and codes.	7 years ago
yangyaming	5ef300f3f0	Make type of error rate optional.	7 years ago
Xinghai Sun	6df0f9bc44	Reset default multi-thread/process number to half of cpu count() for speedup.	7 years ago
Xinghai Sun	8122dd9c29	Simplify train.py, evaluate.py, infer.py and tune.py by adding DeepSpeech2Model class.	7 years ago
Xinghai Sun	92eacf548b	Update default config params and result display for evaluator.py and infer.py for DS2.	7 years ago
Yibing Liu	724ef18596	update several scripts to support mfcc	7 years ago
Yibing Liu	d15c48d616	upload the language model	7 years ago
Yibing Liu	0cadc56a84	follow comments in code format	7 years ago
Yibing Liu	26510f74a6	refine ctc_beam_search_decoder	7 years ago
Yibing Liu	8033845615	add unit test for decoders	7 years ago
Yibing Liu	b2cf96cc46	adapt to the new data provider	7 years ago
Yibing Liu	ff01d048d3	final refining on old data provider: enable pruning & add evaluation & code cleanup	7 years ago