Daniel Povey fca844d80c Make it really have 2k decay and revert to 0.02 scale

2022-06-09 17:45:11 +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

Ignore padding frames during RNN-T decoding. (#358)

2022-05-13 07:39:14 +08:00

conformer.py

Implement JoinDropout

2022-06-08 16:17:42 +08:00

decode.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

decoder.py

Reduce scale on decorrelation by 5, to 0.01

2022-06-07 17:10:54 +08:00

encoder_interface.py

Add remaining files in pruned_transducer_stateless2

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

export.py

Various fixes to support torch script. (#371)

2022-05-16 21:46:59 +08:00

joiner.py

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

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

model.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

optim.py

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

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

pretrained.py

Update results for libri+giga multi dataset setup. (#363)

2022-05-14 21:45:39 +08:00

scaling.py

Make it really have 2k decay and revert to 0.02 scale

2022-06-09 17:45:11 +08:00

test_model.py

Various fixes to support torch script. (#371)

2022-05-16 21:46:59 +08:00

train.py

Improve diagnostics code memory-wise and accumulate more stats. (#373)

2022-05-19 11:45:59 +08:00