Fangjun Kuang 963ac73c27 Add nn.Linear to transform the output of encoder and decoder.

2022-03-11 15:41:03 +08:00

..

__init__.py

Copy files.

2022-03-09 22:36:07 +08:00

asr_datamodule.py

Use giga speech dataset as extra training data.

2022-03-10 10:13:49 +08:00

beam_search.py

Copy files.

2022-03-09 22:36:07 +08:00

conformer.py

Remove extra layer norm in the conformer encoder layer.

2022-03-11 14:48:08 +08:00

decoder.py

Refactor decoder and joiner to remove extra nn.Linear().

2022-03-09 23:06:48 +08:00

encoder_interface.py

Copy files.

2022-03-09 22:36:07 +08:00

gigaspeech.py

Use giga speech dataset as extra training data.

2022-03-10 10:13:49 +08:00

joiner.py

Fix style issues.

2022-03-10 10:21:49 +08:00

librispeech.py

Use giga speech dataset as extra training data.

2022-03-10 10:13:49 +08:00

model.py

Add nn.Linear to transform the output of encoder and decoder.

2022-03-11 15:41:03 +08:00

subsampling.py

Copy files.

2022-03-09 22:36:07 +08:00

test_conformer.py

Remve the last nn.Linear from the transformer model.

2022-03-11 14:21:27 +08:00

test_model.py

Add nn.Linear to transform the output of encoder and decoder.

2022-03-11 15:41:03 +08:00

test_transformer.py

Remve the last nn.Linear from the transformer model.

2022-03-11 14:21:27 +08:00

train.py

Add nn.Linear to transform the output of encoder and decoder.

2022-03-11 15:41:03 +08:00

transformer.py

Add nn.Linear to transform the output of encoder and decoder.

2022-03-11 15:41:03 +08:00