Daniel Povey 4e23fb2252

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

* Update diagnostics, hopefully print more stats.

# Conflicts:
#	egs/librispeech/ASR/pruned_transducer_stateless4b/train.py

* Remove memory-limit options arg

* Remove unnecessary option for diagnostics code, collect on more batches

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

..

__init__.py

GigaSpeech RNN-T experiments (#318)

2022-05-13 11:03:26 +08:00

asr_datamodule.py

GigaSpeech RNN-T experiments (#318)

2022-05-13 11:03:26 +08:00

beam_search.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

conformer.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

decode.py

Update GigaSpeech reults (#364)

2022-05-15 12:57:40 +08:00

decoder.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

encoder_interface.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

export.py

Update GigaSpeech reults (#364)

2022-05-15 12:57:40 +08:00

gigaspeech_scoring.py

GigaSpeech RNN-T experiments (#318)

2022-05-13 11:03:26 +08:00

joiner.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

model.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

optim.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

scaling.py

Update decoding script for gigaspeech and remove duplicate files. (#361)

2022-05-13 13:03:16 +08:00

train.py

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

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