238 Commits

Author SHA1 Message Date
Daniel Povey
ba3611cefd Cosmetic changes to swish 2022-03-18 16:35:48 +08:00
Daniel Povey
6769087d70 Remove scale_speed, make swish deriv more efficient. 2022-03-18 16:31:25 +08:00
Daniel Povey
cbe6b175d1 Reduce warmup scale on pruned loss form 0.1 to 0.01. 2022-03-17 16:46:59 +08:00
Daniel Povey
acc0eda5b0 Scale down pruned loss in warmup mode 2022-03-17 16:09:35 +08:00
Daniel Povey
13db33ffa2 Fix diagnostics-getting code 2022-03-17 15:53:53 +08:00
Daniel Povey
11bea4513e Add remaining files in pruned_transducer_stateless2 2022-03-17 11:17:52 +08:00
Daniel Povey
e3ad8f63e7 update decode.py file type 2022-03-16 22:22:10 +08:00
Daniel Povey
cc8e4412f7 Add more files.. 2022-03-16 22:16:40 +08:00
Daniel Povey
1f3a15f3c4 Start adding some files.. 2022-03-16 22:14:30 +08:00
Daniel Povey
87c92efbfe Changes from upstream/master 2022-03-16 21:49:15 +08:00
Daniel Povey
e838c192ef Cosmetic changes/renaming things 2022-03-16 19:27:45 +08:00
Daniel Povey
dfc75752c4 Remove some dead code. 2022-03-16 18:06:01 +08:00
Daniel Povey
c82db4184a Remove xscale from pos_embedding 2022-03-16 15:50:11 +08:00
Daniel Povey
6561743d7b bug fix re sqrt 2022-03-16 14:55:17 +08:00
Daniel Povey
0e9cad3f1f Modifying initialization from normal->uniform; add initial_scale when initializing 2022-03-16 14:42:53 +08:00
Daniel Povey
00be56c7a0 Remove dead code 2022-03-16 12:49:00 +08:00
Daniel Povey
a783b96467 Fix typo 2022-03-16 12:43:44 +08:00
Daniel Povey
633213424d Rework of initialization 2022-03-16 12:42:59 +08:00
Daniel Povey
1331199530 Merge branch 'specaugmod_baseline' into randcombine1_expscale3_rework2c_maxabs1000_maxp0.95_noexp_convderiv2warmup_scale_0mean 2022-03-15 23:47:03 +08:00
Daniel Povey
261d7602a7 Draft of 0mean changes.. 2022-03-15 23:46:53 +08:00
Daniel Povey
fc873cc50d Make epsilon in BasicNorm learnable, optionally. 2022-03-15 17:00:17 +08:00
Daniel Povey
b2abcd721a Add more stats. 2022-03-15 16:38:19 +08:00
Daniel Povey
1962fe298b Add deriv-balancer at output of embedding. 2022-03-15 14:35:15 +08:00
Daniel Povey
2e6d170be8 Merge branch 'specaugmod_baseline' into randcombine1_expscale3_rework2c_maxabs1000_maxp0.95_noexp_convderiv3warmup_embed 2022-03-15 14:33:08 +08:00
Daniel Povey
21ebd356e7 Add some extra info to diagnostics 2022-03-15 13:49:15 +08:00
Daniel Povey
86e5dcba11 Remove max-positive constraint in deriv-balancing; add second DerivBalancer in conv module. 2022-03-15 13:10:35 +08:00
Daniel Povey
a23010fc10 Add warmup mode 2022-03-14 23:04:51 +08:00
Daniel Povey
8d17a05dd2 Reduce constraints from deriv-balancer in ConvModule. 2022-03-14 19:23:33 +08:00
Daniel Povey
788963d40a Merge branch 'randcombine1_expscale3_rework2c_maxabs1000_maxp0.95_noexp' into randcombine1_expscale3_rework2c_maxabs1000_maxp0.95_noexp_convderiv 2022-03-14 14:37:40 +08:00
Daniel Povey
ae25688253 Make DoubleSwish more memory efficient 2022-03-14 11:02:32 +08:00
Mingshuang Luo
d0d806560f
Change for asr_datamodule.py (#241)
* change for asr_datamodule.py

* fix style check

* do a fix
2022-03-14 00:30:58 +08:00
Daniel Povey
437e8b2083 Reduce max-abs limit from 1000 to 100; introduce 2 DerivBalancer modules in conv layer. 2022-03-13 23:31:08 +08:00
Daniel Povey
f351777e9c Remove ExpScale in feedforward layes. 2022-03-13 17:29:39 +08:00
Daniel Povey
97c0bb82d3 Change dir name 2022-03-13 13:19:20 +08:00
Daniel Povey
5d69acb25b Add max-abs-value 2022-03-13 13:15:20 +08:00
Daniel Povey
e6a501d3c8 Add max-abs-value constraint in DerivBalancer 2022-03-13 11:52:13 +08:00
Daniel Povey
6042c96db2 Use learnable scales for joiner and decoder 2022-03-12 20:54:46 +08:00
Daniel Povey
2117f46361 DoubleSwish fix 2022-03-12 19:02:14 +08:00
Daniel Povey
be0a79cbca Replace ExpScaleRelu with DoubleSwish() 2022-03-12 19:00:48 +08:00
Daniel Povey
db7a3b6eea Reduce initial_scale. 2022-03-12 18:50:02 +08:00
Daniel Povey
b7b2d8970b Cosmetic change 2022-03-12 17:47:35 +08:00
Daniel Povey
a24572abd1 Bug-fix RE bias 2022-03-12 17:28:43 +08:00
Daniel Povey
a392cb9fbc Reduce initial scaling of modules 2022-03-12 16:53:03 +08:00
Fangjun Kuang
bb7f6ed6b7
Add modified beam search for pruned rnn-t. (#248)
* Add modified beam search for pruned rnn-t.

* Fix style issues.

* Update RESULTS.md.

* Fix typos.

* Minor fixes.

* Test the pre-trained model using GitHub actions.

* Let the user install optimized_transducer on her own.

* Fix errors in GitHub CI.
2022-03-12 16:16:55 +08:00
Fangjun Kuang
2f4e71f433
Add force alignment for stateless transducer. (#239)
* Add force alignment for stateless transducer.

* Add more documentation.

* Compute word starting time from framewise token alignment.

* Update README to include force alignment information.

* Fix typos.

* Fix more typos.

* Fixes after review.
2022-03-12 16:16:15 +08:00
Daniel Povey
d906bc2a4f Change dir name 2022-03-12 15:38:39 +08:00
Daniel Povey
ca8cf2a73b Another rework, use scales on linear/conv 2022-03-12 15:38:13 +08:00
Daniel Povey
0abba9e7a2 Fix self.post-scale-mha 2022-03-12 11:20:44 +08:00
Daniel Povey
76a2b9d362 Add learnable post-scale for mha 2022-03-12 11:19:49 +08:00
Daniel Povey
7eb5a84cbe Add identity pre_norm_final for diagnostics. 2022-03-11 21:00:43 +08:00