37 Commits

Author SHA1 Message Date
dohe0342
f4fb761129 from local 2023-02-02 12:39:09 +09:00
dohe0342
da07c74fb6 from local 2023-01-30 14:49:52 +09:00
dohe0342
c56229baf0 from local 2023-01-30 14:49:41 +09:00
dohe0342
152efda5fc from local 2023-01-30 10:52:43 +09:00
dohe0342
916683c649 from local 2023-01-29 19:40:12 +09:00
dohe0342
4aa3796210 from local 2023-01-29 19:34:50 +09:00
dohe0342
1c28ecd7d9 from local 2023-01-29 19:33:39 +09:00
dohe0342
83629cb7d7 from local 2023-01-29 19:31:14 +09:00
dohe0342
eabb297212 from local 2023-01-29 19:28:37 +09:00
dohe0342
8f09b5000e from local 2023-01-28 21:57:45 +09:00
dohe0342
f53344eca1 from local 2023-01-28 21:57:36 +09:00
dohe0342
ce9782650f from local 2023-01-28 21:57:33 +09:00
dohe0342
34588f40a5 from local 2023-01-28 19:27:45 +09:00
dohe0342
dedb6fe5c8 from local 2023-01-28 02:44:19 +09:00
dohe0342
d5408179f6 from local 2023-01-28 02:40:33 +09:00
dohe0342
8f1fdada00 from local 2023-01-09 13:02:49 +09:00
dohe0342
cec98fd855 from local 2023-01-05 17:57:48 +09:00
dohe0342
b4e6fdb4be from local 2023-01-04 23:27:00 +09:00
dohe0342
807139dfad from local 2023-01-04 23:25:50 +09:00
dohe0342
eff87e2fb6 from local 2023-01-04 00:12:26 +09:00
dohe0342
9c7d1256f8 from local 2023-01-04 00:11:22 +09:00
dohe0342
3fa5cf942c from local 2023-01-04 00:11:02 +09:00
dohe0342
88f0e738b9 from local 2023-01-03 22:42:11 +09:00
dohe0342
e97bb032bb from local 2023-01-03 22:41:43 +09:00
dohe0342
755b1a4cbb from local 2023-01-03 22:41:12 +09:00
dohe0342
0f88dcfa99 from local 2023-01-03 22:41:04 +09:00
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
d110b04ad3 apply new black formatting to all files 2022-11-16 13:06:43 -05:00
LIyong.Guo
923b60a7c6
padding zeros (#591) 2022-09-28 21:20:33 +08:00
Wei Kang
2f75236c05
Support dynamic chunk streaming training in pruned_transcuder_stateless5 (#454)
* support dynamic chunk streaming training

* Add simulate streaming decoding

* Support streaming decoding

* fix causal

* Minor fixes

* fix streaming decode; add results
2022-07-29 16:40:06 +08:00
Zengwei Yao
ce26495238
Rand combine update result (#467)
* update RESULTS.md

* fix test code in pruned_transducer_stateless5/conformer.py

* minor fix

* delete doc

* fix style
2022-07-11 18:13:31 +08:00
Zengwei Yao
d80f29e662
Modification about random combine (#452)
* comment some lines, random combine from 1/3 layers, on linear layers in combiner

* delete commented lines

* minor change
2022-06-30 12:23:49 +08:00
Jun Wang
d792bdc9bc
fix typo (#445) 2022-06-25 11:00:53 +08:00
Tiance Wang
c0ea334738
fix bug of concatenating list to tuple (#444) 2022-06-24 19:31:09 +08:00
Fangjun Kuang
7100c33820
Add pruned RNN-T for aishell. (#436)
* Add pruned RNN-T for aishell.

* support torch script.

* Update CI.

* Minor fixes.

* Add links to sherpa.
2022-06-21 21:17:22 +08:00
Fangjun Kuang
2f1e23cde1
Narrower and deeper conformer (#330)
* Copy files for editing.

* Add random combine from #229.

* Minor fixes.

* Pass model parameters from the command line.

* Fix warnings.

* Fix warnings.

* Update readme.

* Rename to avoid conflicts.

* Update results.

* Add CI for pruned_transducer_stateless5

* Typo fixes.

* Remove random combiner.

* Update decode.py and train.py to use periodically averaged models.

* Minor fixes.

* Revert to use random combiner.

* Update results.

* Minor fixes.
2022-05-23 14:39:11 +08:00