Yuekai Zhang 1c30847947

Whisper Fine-tuning Recipe on Aishell1 (#1466) ...

* add decode seamlessm4t

* add requirements

* add decoding with avg model

* add token files

* add custom tokenizer

* support deepspeed to finetune large model

* support large-v3

* add model saving

* using monkey patch to replace models

* add manifest dir option

2024-01-27 00:32:30 +08:00

..

__init__.py

WIP: Begin to add BPE decoding

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

add_alignment_librispeech.py

apply black on all files

2022-11-17 09:42:17 -05:00

compile_hlg_using_openfst.py

not removing result_dir in tedlium conformer ctc2 + add lm stem to compile_hlg_using_openfst.py + add MASTER_ADDR to be prvided to setup_dist (#801)

2023-01-02 08:08:32 +08:00

compile_hlg.py

fix compiling HLG (#1039)

2023-05-07 16:26:13 +08:00

compile_lg.py

fix compiling HLG (#1039)

2023-05-07 16:26:13 +08:00

compute_fbank_gigaspeech_dev_test.py

apply black on all files

2022-11-17 09:42:17 -05:00

compute_fbank_gigaspeech_splits.py

apply black on all files

2022-11-17 09:42:17 -05:00

compute_fbank_librispeech.py

Add multidataset (#1010)

2023-04-21 18:09:41 +08:00

compute_fbank_musan.py

Whisper Fine-tuning Recipe on Aishell1 (#1466)

2024-01-27 00:32:30 +08:00

convert_transcript_words_to_tokens.py

apply black on all files

2022-11-17 09:42:17 -05:00

display_manifest_statistics.py

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

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

download_lm.py

formatted the entire LibriSpeech recipe (#1270)

2023-09-24 17:31:01 +08:00

filter_cuts.py

manual correction of black formatting

2022-11-17 14:18:05 -05:00

generate_unique_lexicon.py

apply black on all files

2022-11-17 09:42:17 -05:00

prepare_lang_bpe.py

Tedlium3 conformer ctc2 (#696)

2022-12-13 16:13:26 +08:00

prepare_lang_fst.py

Support HLG decoding using OpenFst with kaldi decoders (#1275)

2023-09-27 14:49:27 +08:00

prepare_lang.py

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

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

prepare_lm_training_data.py

manual correction of black formatting

2022-11-17 14:18:05 -05:00

preprocess_gigaspeech.py

apply black on all files

2022-11-17 09:42:17 -05:00

sort_lm_training_data.py

[Ready to be merged] Add RNN-LM to Conformer-CTC decoding (#439)

2022-06-23 19:37:03 +08:00

test_load_XL_split.py

Modified conformer with multi datasets (#312)

2022-04-29 15:40:30 +08:00

test_prepare_lang.py

apply black on all files

2022-11-17 09:42:17 -05:00

train_bpe_model.py

Fix CI (#726)

2022-12-02 10:53:06 +08:00

validate_bpe_lexicon.py

Validate that there are no OOV tokens in BPE-based lexicons. (#359)

2022-05-13 14:00:35 +08:00

validate_manifest.py

Librispeech, validate_manifest.py (#890)

2023-02-09 07:57:02 +08:00