805846ce67
Reduce the config parsing codes for DS2 and make it looks cleaner.
8 years ago
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.
8 years ago
177af05953
Fix a bug in use_gru argument parsing.
8 years ago
5a63275845
Add GRU support.
8 years ago
6df0f9bc44
Reset default multi-thread/process number to half of cpu count() for speedup.
8 years ago
526e18b119
Add function docs for layer.py and model.py and update other details.
8 years ago
8122dd9c29
Simplify train.py, evaluate.py, infer.py and tune.py by adding DeepSpeech2Model class.
8 years ago
724ef18596
update several scripts to support mfcc
8 years ago
d15c48d616
upload the language model
8 years ago
0cadc56a84
follow comments in code format
8 years ago
37e98df74d
enable resetting params in scorer
8 years ago
26510f74a6
refine ctc_beam_search_decoder
8 years ago
8033845615
add unit test for decoders
8 years ago
b2cf96cc46
adapt to the new data provider
8 years ago
ff01d048d3
final refining on old data provider: enable pruning & add evaluation & code cleanup
8 years ago
7db13ca9db
enable lm in multiprocessing decoder & add script for params tuning
8 years ago
Xinghai Sun
Yibing Liu