Daniil b293db4baf

Tedlium3 conformer ctc2 (#696) ...

* modify preparation

* small refacor

* add tedlium3 conformer_ctc2

* modify decode

* filter unk in decode

* add scaling converter

* address comments

* fix lambda function lhotse

* add implicit manifest shuffle

* refactor ctc_greedy_search

* import model arguments from train.py

* style fix

* fix ci test and last style issues

* update RESULTS

* fix RESULTS numbers

* fix label smoothing loss

* update model parameters number in RESULTS

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

..

__init__.py

Tedlium3 transducer stateless (#233)

2022-03-18 11:39:06 +08:00

compile_hlg.py

Tedlium3 transducer stateless (#233)

2022-03-18 11:39:06 +08:00

compute_fbank_musan.py

Tedlium3 transducer stateless (#233)

2022-03-18 11:39:06 +08:00

compute_fbank_tedlium.py

apply black on all files

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

convert_transcript_words_to_bpe_ids.py

Tedlium3 conformer ctc2 (#696)

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

display_manifest_statistics.py

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

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

prepare_lang_bpe.py

Tedlium3 transducer stateless (#233)

2022-03-18 11:39:06 +08:00

prepare_transcripts.py

Tedlium3 conformer ctc2 (#696)

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

prepare_words.py

Tedlium3 conformer ctc2 (#696)

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

train_bpe_model.py

Tedlium3 transducer stateless (#233)

2022-03-18 11:39:06 +08:00