dohe0342
bcc2da0a18
from local
2022-12-09 17:16:37 +09:00
dohe0342
0faf0476b6
from local
2022-12-09 17:16:09 +09:00
dohe0342
03e81c52f2
from local
2022-12-09 17:16:01 +09:00
dohe0342
1506d6f13f
from local
2022-12-09 17:15:45 +09:00
dohe0342
fbcae11a6f
from local
2022-12-09 17:14:19 +09:00
dohe0342
9efa39bb39
from local
2022-12-09 17:12:17 +09:00
dohe0342
321fe7f525
from local
2022-12-09 17:12:01 +09:00
dohe0342
d06daa88e8
from local
2022-12-09 17:11:57 +09:00
dohe0342
672a3693b3
from local
2022-12-09 17:11:11 +09:00
dohe0342
de5402e2c8
from local
2022-12-09 17:10:42 +09:00
dohe0342
561d018f6b
from local
2022-12-09 17:10:31 +09:00
dohe0342
73c8e31fd1
from local
2022-12-09 17:10:08 +09:00
dohe0342
49fbef1203
from local
2022-12-09 17:08:29 +09:00
dohe0342
217bd54639
from local
2022-12-09 17:07:27 +09:00
dohe0342
a1a1964b95
from local
2022-12-09 17:05:03 +09:00
dohe0342
a1840e672a
from local
2022-12-09 17:00:05 +09:00
dohe0342
998c206fec
from local
2022-12-09 16:55:10 +09:00
dohe0342
c39b9f8220
from local
2022-12-09 16:54:58 +09:00
dohe0342
cc370fd9c1
from local
2022-12-09 16:33:10 +09:00
dohe0342
dfe76b31bd
from local
2022-12-09 16:28:07 +09:00
dohe0342
9143547bf2
from local
2022-12-09 16:25:00 +09:00
dohe0342
1f6ff8a453
from local
2022-12-09 16:24:57 +09:00
dohe0342
2af859afa8
from local
2022-12-09 15:58:12 +09:00
dohe0342
3c1957c20b
from local
2022-12-09 15:58:01 +09:00
dohe0342
2709e500e7
from local
2022-12-09 15:57:56 +09:00
dohe0342
c9359eff88
from local
2022-12-09 15:57:44 +09:00
dohe0342
0982e809a3
from local
2022-12-09 15:53:58 +09:00
armusc
d65fe17d27
Update train.py with parameters_names as required by optimizer initialization ( #742 )
...
* Update train.py
2022-12-08 20:21:51 +08:00
Fangjun Kuang
f13cf61b05
Convert conv-emformer to ncnn ( #717 )
...
* Export conv-emformer via torch.jit.trace()
2022-12-06 16:34:27 +08:00
Wei Kang
c25c8c6ad1
Add need_repeat_flag in phone based ctc graph compiler ( #727 )
...
* Fix is_repeat_token in icefall
* Fix phone based recipe
* Update egs/librispeech/ASR/conformer_ctc3/train.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* Fix black
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2022-12-04 17:20:17 +08:00
Zengwei Yao
8eb4b9d96d
Combining rnnt loss and k2-ctc loss for Dan's Zipformer ( #683 )
...
* init files
* add ctc as auxiliary loss and ctc_decode.py
* tuning the scalar of HLG score for 1best, nbest and nbest-oracle
* rename to pruned_transducer_stateless7_ctc
* fix doc
* fix bug, recover the hlg scores
* modify ctc_decode.py, move out the hlg scale
* fix hlg_scale
* add export.py and pretrained.py, and so on
* upload files, update README.md and RESULTS.md
* add CI test
2022-12-03 19:01:10 +08:00
Weiji Zhuang
7700ddcb38
update multidataset zipformer results ( #728 )
2022-12-02 17:40:42 +08:00
Fangjun Kuang
6533f359c9
Fix CI ( #726 )
...
* Fix CI
* Disable shuffle for yesno.
See https://github.com/k2-fsa/icefall/issues/197
2022-12-02 10:53:06 +08:00
Fangjun Kuang
2bca7032af
Update RNNLM training scripts ( #720 )
...
* Update RNNLM training scripts
* Fix a typo
* Fix CI
2022-12-01 15:57:43 +08:00
marcoyang1998
4b5bc480e8
Add low-order density ratio in RNNLM shallow fusion ( #678 )
...
* Support LODR in RNNLM shallow fusion
* fix style
* fix code style
* update workflow and CI
* update results
* propagate changes to stateless3
* add decoding results for stateless3+giga
* fix CI
2022-11-30 17:26:05 +08:00
Daniel Povey
1d5c03f85a
Merge pull request #705 from glynpu/improve_diagnostic
...
[ready]show dominant parameters
2022-11-29 20:00:52 +08:00
Zengwei Yao
ece728d895
Apply delay penalty on k2 ctc loss ( #669 )
...
* add init files
* fix bug, apply delay penalty
* fix decoding code and getting timestamps
* add option applying delay penalty on ctc log-prob
* fix bug of streaming decoding
* minor change for bpe-based case
* add test_model.py
* add README.md
* add CI
2022-11-28 22:34:02 +08:00
Guo Liyong
4fee3e7f1e
impove comment
2022-11-28 17:33:52 +08:00
huangruizhe
6693d907d3
shuffle full Librispeech data ( #574 )
...
* shuffled full/partial librispeech data
* fixed the code style issue
* Shuffled full librispeech data off-line
* Fixed style, addressed comments, and removed redandunt codes
* Used the suggested version of black
* Propagated the changes to other folders for librispeech (except
conformer_mmi and streaming_conformer_ctc)
2022-11-27 11:26:09 +08:00
Guo Liyong
9cf79cac3f
message formatting
2022-11-26 22:39:03 +08:00
Guo Liyong
89c3982a07
show dominant parameters
2022-11-26 00:50:21 +08:00
Senyan Li
4c636c2cff
fix librispeech ASR pruned_transducer_stateless5 export ( #704 )
2022-11-25 14:39:56 +08:00
marcoyang
53454701cb
fix segmentation fault
2022-11-22 11:39:21 +08:00
Desh Raj
d31db01037
manual correction of black formatting
2022-11-17 14:18:05 -05:00
Desh Raj
107df3b115
apply black on all files
2022-11-17 09:42:17 -05:00
Fangjun Kuang
60317120ca
Revert "Apply new Black style changes"
2022-11-17 20:19:32 +08:00
Desh Raj
cad8f6aca4
merge upstream
2022-11-16 19:50:43 -05:00
Daniil
fca796cc2c
Small code refactoring ( #687 )
2022-11-17 06:55:53 +08:00
Desh Raj
d110b04ad3
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
Desh Raj
c8ce243255
Zipformer output length ( #686 )
...
* add assertion for output length
* add comment in filter_cuts
* add length filter to Zipformer recipes
2022-11-16 11:29:45 +08:00
