Fangjun Kuang dc89b61b80

Add fast_beam_search_nbest. (#420) ...

* Add fast_beam_search_nbest.

* Fix CI errors.

* Fix CI errors.

* More fixes.

* Small fixes.

* Support using log_add in LG decoding with fast_beam_search.

* Support LG decoding in pruned_transducer_stateless

* Support LG for pruned_transducer_stateless2.

* Support LG for fast beam search.

* Minor fixes.

2022-06-22 00:09:25 +08:00

..

dataset

Add recipe for the yes_no dataset. (#16)

2021-08-23 11:36:29 +08:00

shared

minor fixes

2022-01-02 23:38:33 -08:00

__init__.py

Modify init (#301)

2022-04-10 23:29:28 +08:00

ali.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

bpe_graph_compiler.py

Fix code style and add copyright. (#18)

2021-08-23 10:43:59 +08:00

char_graph_compiler.py

Minor fixes for aishell (#218)

2022-02-19 22:28:19 +08:00

checkpoint.py

Support decoding with averaged model when using --iter (#353)

2022-05-07 13:09:11 +08:00

decode.py

Add fast_beam_search_nbest. (#420)

2022-06-22 00:09:25 +08:00

diagnostics.py

[Ready to merge] Do some coding style checks for the latest files (#379)

2022-05-20 19:30:38 +08:00

dist.py

Fix code style and add copyright. (#18)

2021-08-23 10:43:59 +08:00

env.py

Stringify torch.__version__ before serializing it. (#354)

2022-05-07 17:18:34 +08:00

graph_compiler.py

black

2022-01-21 17:22:41 -05:00

lexicon.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

mmi_graph_compiler.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

mmi.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

utils.py

Use jsonl for CutSet in the LibriSpeech recipe. (#397)

2022-06-06 10:19:16 +08:00