icefall

mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 18:12:19 +00:00

History

Support pure ctc decoding requiring neither a lexicon nor an n-gram LM (#58 )

* Rename lattice_score_scale to nbest_scale.

* Support pure CTC decoding requiring neither a lexicion nor an n-gram LM.

* Fix style issues.

* Fix a typo.

* Minor fixes.

2021-09-26 14:21:49 +08:00

__init__.py

WIP: Begin to add BPE decoding

2021-07-26 20:06:58 +08:00

asr_datamodule.py

Refactor asr_datamodule. (#15 )

2021-08-21 09:53:46 +08:00

conformer.py

Refactor decode.py to make it more readable and more modular. (#44 )

2021-09-20 15:44:54 +08:00

decode.py

Support pure ctc decoding requiring neither a lexicon nor an n-gram LM (#58 )

2021-09-26 14:21:49 +08:00

pretrained.py

Support pure ctc decoding requiring neither a lexicon nor an n-gram LM (#58 )

2021-09-26 14:21:49 +08:00

README.md

Add TDNN-LSTM-CTC Results (#25 )

2021-08-24 21:09:27 +08:00

subsampling.py

Refactor decode.py to make it more readable and more modular. (#44 )

2021-09-20 15:44:54 +08:00

test_subsampling.py

Use new APIs with k2.RaggedTensor (#38 )

2021-09-08 14:55:30 +08:00

test_transformer.py

Use new APIs with k2.RaggedTensor (#38 )

2021-09-08 14:55:30 +08:00

train.py

Refactor decode.py to make it more readable and more modular. (#44 )

2021-09-20 15:44:54 +08:00

transformer.py

Refactor decode.py to make it more readable and more modular. (#44 )

2021-09-20 15:44:54 +08:00

README.md

Please visit https://icefall.readthedocs.io/en/latest/recipes/librispeech/conformer_ctc.html for how to run this recipe.