mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-13 02:54:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
994 Commits 5 Branches 3 Tags
Commit Graph

994 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
marcoyang
02e812300b update documentation for PromptASR 2023-10-19 17:22:43 +08:00
marcoyang
30c1a19a9b update documentation for PromptASR 2023-10-19 17:17:51 +08:00
Erwan Zerhouni
807816fec0
Fix chunk issue for sherpa (#1316) 2023-10-18 16:07:10 +08:00
zr_jin
d2bd0933b1
Compatibility with the latest Lhotse (#1314) 2023-10-17 21:22:32 +08:00
zr_jin
1ef349d120
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300) 
* `pruned_transudcer_stateless7_streaming` for AISHELL-1

* Update train.py

* Update train2.py

* Update decode.py

* Update RESULTS.md
 2023-10-16 16:28:16 +08:00
zr_jin
eeeeef390b
Minor bug fixes and descriptive text for the LibriCSS recipe (#1268) 2023-10-12 10:02:49 -04:00
zr_jin
162ceaf4b3
fixes for data preparation (#1307) 
Issue: #1306
 2023-10-12 17:05:41 +08:00
zr_jin
855492156a
Update finetune.py (#1304) 2023-10-12 16:48:23 +08:00
Wen Ding
2b3c5d799f
Fix padding issues (#1303) 2023-10-11 16:58:00 +08:00
marcoyang1998
16a2748d6c
PromptASR for contextualized ASR with controllable style (#1250) 
* Add PromptASR with BERT as text encoder

* Support using word-list based content prompts for context biasing

* Upload the pretrained models to huggingface

* Add usage example
 2023-10-11 14:56:41 +08:00
marcoyang
b21e4da943 minor fixes 2023-10-11 14:40:39 +08:00
Fangjun Kuang
cb874e9905
add export-onnx.py for stateless8 (#1302) 
* add export-onnx.py for stateless8

* use tokens.txt to replace bpe.model
 2023-10-11 12:20:12 +08:00
marcoyang
9416dde02f add pretrained.py 2023-10-11 12:11:17 +08:00
zr_jin
103d617380
bug fixes (#1301) 2023-10-11 11:04:20 +08:00
marcoyang
51d9c4f028 refactor code 2023-10-11 10:54:40 +08:00
zr_jin
0d09a44930
Update train.py (#1299) 2023-10-11 10:06:00 +08:00
marcoyang
77fc1c0929 fix typo 2023-10-11 09:48:00 +08:00
marcoyang
03a632fc30 Merge branch 'master' of github.com:marcoyang1998/icefall into libriheavy_prompt_asr 2023-10-11 09:46:43 +08:00
marcoyang
96977c9ddd fix for black 2023-10-10 17:44:48 +08:00
marcoyang
e32bda6a7b fix style 2023-10-10 16:55:31 +08:00
marcoyang
90dac69bc5 fix optim.py 2023-10-10 16:51:07 +08:00
marcoyang
9ef5dfe380 fix style 2023-10-10 16:48:17 +08:00
marcoyang
7a9c18fc79 update training script 2023-10-10 16:42:22 +08:00
marcoyang
9f48d06581 update RESULTS.md 2023-10-10 16:41:34 +08:00
marcoyang
35aab79e3d support exporting model state dict 2023-10-10 16:40:54 +08:00
Zengwei Yao
9af144c26b
Zipformer update result (#1296) 
* update Zipformer results
 2023-10-09 23:15:22 +08:00
zr_jin
fefffc02f6
Update optim.py (#1292) 2023-10-09 17:39:23 +08:00
marcoyang
838c24cba1 fix bug in decode 2023-10-07 16:04:53 +08:00
zr_jin
ce08230ade
Update README.md (#1293) 2023-10-07 11:57:30 +08:00
zr_jin
82199b8fe1
Init commit for swbd (#1146) 2023-10-07 11:44:18 +08:00
marcoyang
7c56d8f06b fix a bug in samping function 2023-10-04 00:09:27 +08:00
Fangjun Kuang
109354b6b8
Add CTC HLG decoding for zipformer (#1287) 2023-10-02 14:00:06 +08:00
Fangjun Kuang
f14b673408
Add HLG decoding with OpenFst on CPU for aishell conformer_ctc (#1279) 2023-10-01 13:46:16 +08:00
Fangjun Kuang
48cc41bd83 Fix CI 2023-09-30 22:23:22 +08:00
Dongji Gao
3abc290c11
Add scripts and recipe for BTC/OTC (#1255) 2023-09-29 07:52:46 +08:00
yaguang
8181d19860
check bbpe model exists in advance. (#1277) 2023-09-27 17:35:26 +08:00
yaguang
a5ba1133c4
Compatible with new lhotse versions. (#1278) 2023-09-27 17:33:38 +08:00
Fangjun Kuang
772ee3955b
Support HLG decoding using OpenFst with kaldi decoders (#1275) 2023-09-27 14:49:27 +08:00
marcoyang
e058ba0a65 minor updates 2023-09-27 11:31:14 +08:00
Fangjun Kuang
2318c3fbd0
Support CTC decoding on CPU using OpenFst and kaldi decoders. (#1244) 2023-09-26 16:36:19 +08:00
zr_jin
1b565dd251
added softlinks to local dir (#1273) 2023-09-26 15:41:39 +08:00
marcoyang1998
e17f884ace
Fix docs for MVQ (#1272) 
* typo fix
 2023-09-25 15:36:40 +08:00
marcoyang1998
97f9b9c33b
Add documentation for RNNLM training (#1267) 
* add documentation for training an RNNLM
 2023-09-25 10:48:50 +08:00
zr_jin
ef5da4824d
formatted the entire LibriSpeech recipe (#1270) 
* formatted the entire librispeech recipe

* minor updates
 2023-09-24 17:31:01 +08:00
zr_jin
ef658d691e
fixes for init value of diagnostics.TensorDiagnosticOptions (#1269) 
* fixes for `diagnostics`

Replace `2 ** 22` with `512` as the default value of `diagnostics.TensorDiagnosticOptions`

also black formatted some scripts

* fixed formatting issues
 2023-09-24 17:06:47 +08:00
Fangjun Kuang
34e40a86b3
Fix exporting decoder model to onnx (#1264) 
* Use torch.jit.script() to export the decoder model

See also https://github.com/k2-fsa/sherpa-onnx/issues/327
 2023-09-22 09:57:15 +08:00
Fangjun Kuang
f5dc957d44
Fix CI tests (#1266) 2023-09-21 21:16:14 +08:00
l2009312042
45d60ef262
Update conformer.py (#1200) 
* Update conformer.py
* Update zipformer.py

fix bug in get_dynamic_dropout_rate
 2023-09-21 19:41:10 +08:00
marcoyang
ae3149cb7f freeze BERT option 2023-09-21 10:24:14 +08:00
marcoyang
21cc1dfff4 fix lhotse compatibility 2023-09-21 10:22:56 +08:00