PaddleSpeech

Author	SHA1	Message	Date
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	c8530dbbe8	Merge branch 'develop' into network_structure	7 years ago
Xinghai Sun	aed0cc991f	Fixed a bug of mixing forward and backward projection in bi-directional GRUs.	7 years ago
Xinghai Sun	1d163ad15f	Fixed a serious mistake of bidirectional simple rnn for DS2.	7 years ago
Xinghai Sun	d7a2c0e990	Replace activator BRelu with Relu.	7 years ago
Xinghai Sun	5a63275845	Add GRU support.	7 years ago
Xinghai Sun	526e18b119	Add function docs for layer.py and model.py and update other details.	7 years ago
Xinghai Sun	8122dd9c29	Simplify train.py, evaluate.py, infer.py and tune.py by adding DeepSpeech2Model class.	7 years ago