Zengwei Yao c059ef3169

Keep model_avg on cpu (#348) ...

* keep model_avg on cpu

* explicitly convert model_avg to cpu

* minor fix

* remove device convertion for model_avg

* modify usage of the model device in train.py

* change model.device to next(model.parameters()).device for decoding

* assert params.start_epoch>0

* assert params.start_epoch>0, params.start_epoch

2022-05-07 10:42:34 +08:00

..

__init__.py

Start adding some files..

2022-03-16 22:14:30 +08:00

asr_datamodule.py

Start adding some files..

2022-03-16 22:14:30 +08:00

beam_search.py

Keep model_avg on cpu (#348)

2022-05-07 10:42:34 +08:00

conformer.py

Code style check for librispeech pruned transducer stateless2 (#308)

2022-04-11 22:15:18 +08:00

decode.py

Modified conformer with multi datasets (#312)

2022-04-29 15:40:30 +08:00

decoder.py

Code style check for librispeech pruned transducer stateless2 (#308)

2022-04-11 22:15:18 +08:00

encoder_interface.py

Add remaining files in pruned_transducer_stateless2

2022-03-17 11:17:52 +08:00

export.py

Fix dir names

2022-04-11 12:03:41 +08:00

joiner.py

Code style check for librispeech pruned transducer stateless2 (#308)

2022-04-11 22:15:18 +08:00

model.py

Code style check for librispeech pruned transducer stateless2 (#308)

2022-04-11 22:15:18 +08:00

optim.py

Code style check for librispeech pruned transducer stateless2 (#308)

2022-04-11 22:15:18 +08:00

pretrained.py

Modified conformer with multi datasets (#312)

2022-04-29 15:40:30 +08:00

scaling.py

fix comments

2022-04-13 13:09:24 +08:00

train.py

Save batch to disk on exception. (#350)

2022-05-06 17:49:40 +08:00