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

..

aidatatang_200zh/ASR

Fix torchscript export to use tokens.txt instead of lang_dir (#1475)

2024-01-26 19:18:33 +08:00

aishell/ASR

Whisper Fine-tuning Recipe on Aishell1 (#1466)

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

aishell2/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

aishell4/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

alimeeting

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

ami

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

commonvoice/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

csj/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

gigaspeech/ASR

Fix torchscript export to use tokens.txt instead of lang_dir (#1475)

2024-01-26 19:18:33 +08:00

libricss/SURT

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

libriheavy/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

librispeech

Whisper Fine-tuning Recipe on Aishell1 (#1466)

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

ljspeech/TTS

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

mgb2/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

multi_zh_en/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

multi_zh-hans/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

must_c/ST

Add data preparation for the MuST-C speech translation corpus (#1107)

2023-06-05 15:49:41 +08:00

peoples_speech/ASR

typos fixed (#1472)

2024-01-25 18:41:43 +08:00

ptb/LM

Update train-rnn-lm.sh (#1337)

2023-10-25 12:50:35 +08:00

spgispeech/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

swbd/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

tal_csasr/ASR

Fix torchscript export to use tokens.txt instead of lang_dir (#1475)

2024-01-26 19:18:33 +08:00

tedlium3/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

timit/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

vctk/TTS

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

voxpopuli/ASR

add the voxpopuli recipe (#1374)

2023-11-16 14:38:31 +08:00

wenetspeech/ASR

Fix torchscript export to use tokens.txt instead of lang_dir (#1475)

2024-01-26 19:18:33 +08:00

xbmu_amdo31/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

yesno/ASR

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00