Fangjun Kuang 89a08b64ce Remove long utterances to avoid OOM when a large max_duraiton is used.

2021-12-13 16:41:14 +08:00

..

__init__.py

WIP: Begin to add BPE decoding

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

compile_hlg.py

Set fsa.properties to None after changing its labels in-place. (#121)

2021-11-16 23:11:30 +08:00

compute_fbank_librispeech.py

Add recipe for the yes_no dataset. (#16)

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

compute_fbank_musan.py

Add recipe for the yes_no dataset. (#16)

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

convert_transcript_words_to_tokens.py

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

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

display_manifest_statistics.py

Remove long utterances to avoid OOM when a large max_duraiton is used.

2021-12-13 16:41:14 +08:00

download_lm.py

Fix code style and add copyright. (#18)

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

generate_unique_lexicon.py

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

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

prepare_lang_bpe.py

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

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

prepare_lang.py

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

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

test_prepare_lang.py

Fix code style and add copyright. (#18)

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

train_bpe_model.py

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

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