Wei Kang 711d6bc462

Refactor prepare.sh in librispeech (#1493) ...

* Refactor prepare.sh in librispeech, break it into three parts,  prepare.sh (basic, minimal requirement for transducer), prepare_lm.sh (ngram & nnlm staff), prepare_mmi.sh (for MMI training).

2024-02-09 10:44:19 +08:00

..

__init__.py

…

add_alignment_librispeech.py

…

compile_hlg_using_openfst.py

…

compile_hlg.py

…

compile_lg.py

…

compute_fbank_gigaspeech_dev_test.py

…

compute_fbank_gigaspeech_splits.py

…

compute_fbank_librispeech.py

…

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

…

display_manifest_statistics.py

…

download_lm.py

formatted the entire LibriSpeech recipe (#1270)

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

filter_cuts.py

…

generate_unique_lexicon.py

…

prepare_lang_bpe.py

…

prepare_lang_fst.py

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

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

prepare_lang.py

…

prepare_lm_training_data.py

…

preprocess_gigaspeech.py

…

sort_lm_training_data.py

…

test_load_XL_split.py

…

test_prepare_lang.py

…

train_bpe_model.py

Refactor prepare.sh in librispeech (#1493)

2024-02-09 10:44:19 +08:00

validate_bpe_lexicon.py

…

validate_manifest.py

…