You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Hui Zhang
b3bc451328
remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639)
* remove sequnce_mask
* format
* fix ds2 export audio shape from B,D,T to B,T,D
|
4 years ago |
.. |
__init__.py
|
Support paddle 2.x (#538)
|
4 years ago |
activation.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
attention.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
cmvn.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
conformer_convolution.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
conv.py
|
remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639)
|
4 years ago |
ctc.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
decoder.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
decoder_layer.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
embedding.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
encoder.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
encoder_layer.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
loss.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
mask.py
|
remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639)
|
4 years ago |
positionwise_feed_forward.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |
rnn.py
|
remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639)
|
4 years ago |
subsampling.py
|
E2E/Streaming Transformer/Conformer ASR (#578)
|
4 years ago |