505 Commits

Author SHA1 Message Date
Daniel Povey
6085ab64ef Make cain average over more iters and use preconditioning on the other dims first 2022-05-19 21:34:12 +08:00
Daniel Povey
ac5a9faafd Merge branch 'master' into knowledge_base_1b_L2_ng_orth2feat_cain 2022-05-19 12:49:24 +08:00
Daniel Povey
9e88d0bf31 Merge remote-tracking branch 'upstream/master' 2022-05-19 12:49:12 +08:00
Daniel Povey
5230e73e41 Small fixes 2022-05-19 12:49:00 +08:00
Daniel Povey
e44edf99a4 Merge branch 'master' into knowledge_base_1b_L2_ng_orth2feat_cain 2022-05-19 12:42:50 +08:00
Daniel Povey
4e23fb2252
Improve diagnostics code memory-wise and accumulate more stats. (#373)
* Update diagnostics, hopefully print more stats.

# Conflicts:
#	egs/librispeech/ASR/pruned_transducer_stateless4b/train.py

* Remove memory-limit options arg

* Remove unnecessary option for diagnostics code, collect on more batches
2022-05-19 11:45:59 +08:00
Daniel Povey
c736b39c7d Remove unnecessary option for diagnostics code, collect on more batches 2022-05-19 11:35:54 +08:00
Daniel Povey
c0fdfabaf3 Remove memory-limit options arg 2022-05-19 11:30:56 +08:00
Daniel Povey
c2c46ea023 Update diagnostics, hopefully print more stats.
# Conflicts:
#	egs/librispeech/ASR/pruned_transducer_stateless4b/train.py
2022-05-19 11:29:31 +08:00
Daniel Povey
ebc2ffeff7 Bug fix 2022-05-18 10:26:29 +08:00
Daniel Povey
668d01cc7a Replace Eve with Cain in pruned_transducer_stateless4 2022-05-18 10:16:50 +08:00
Daniel Povey
38ccbb6062 Think it works now.. will move to different branch though. 2022-05-18 10:11:20 +08:00
Daniel Povey
3d35018ce0 Just adding some draft code, will move this around. 2022-05-17 21:00:36 +08:00
Daniel Povey
a46f74feb4 Broadcast transformation 2022-05-17 17:23:28 +08:00
Daniel Povey
ceb4eb4b85 Scale covariance 2022-05-17 15:32:06 +08:00
Daniel Povey
c923b5900e Symmetrize covariance 2022-05-17 15:14:23 +08:00
Daniel Povey
9133b57808 Use torch.no_grad() for stats 2022-05-17 14:49:00 +08:00
Daniel Povey
07d3369234 Finish feat-diagonalizing code 2022-05-17 14:13:56 +08:00
Fangjun Kuang
f6ce135608
Various fixes to support torch script. (#371)
* Various fixes to support torch script.

* Add tests to ensure that the model is torch scriptable.

* Update tests.
2022-05-16 21:46:59 +08:00
Desh Raj
5aafbb970e
SPGISpeech recipe (#334)
* initial commit for SPGISpeech recipe

* add decoding

* add spgispeech transducer

* remove conformer ctc; minor fixes in RNN-T

* add results

* add tensorboard

* add pretrained model to HF

* remove unused scripts and soft link common scripts

* remove duplicate files

* pre commit hooks

* remove change in librispeech

* pre commit hook

* add CER numbers
2022-05-16 20:52:14 +08:00
Daniel Povey
2f2934a115 fix train.py 2022-05-16 19:41:16 +08:00
Daniel Povey
d61c8aa3bc Hopefully this finishes the full orthogonalization. 2022-05-16 19:18:12 +08:00
Daniel Povey
67f916e599 Draft towards 2nd orthogonalization 2022-05-16 16:16:12 +08:00
Daniel Povey
8aeaf1421a Rename orthogonalize to diagonalize 2022-05-16 12:43:47 +08:00
Daniel Povey
9859e33c06 Remove optimizer.reset() which is not supported for Eve 2022-05-16 12:13:36 +08:00
Daniel Povey
d58debdb3f Use Eve with orthogonalization 2022-05-16 10:34:25 +08:00
Daniel Povey
995371ad95 Move train.py changes to the right dir 2022-05-15 22:17:08 +08:00
Daniel Povey
cee5396058 Orthogonalize every 2k iters 2022-05-15 21:50:40 +08:00
Daniel Povey
bb32556f9e Add and test reset() function 2022-05-15 16:20:10 +08:00
Daniel Povey
a1dc020270 train scalars slower 2022-05-15 15:44:56 +08:00
Daniel Povey
0989aec741 Replace Eve optimizer with Abel. 2022-05-15 14:33:08 +08:00
Fangjun Kuang
6f7860a0a6
Fix GitHub CI for decoding GigaSpeech dev/test datasets (#366) 2022-05-15 14:25:35 +08:00
Daniel Povey
5e3bf4ce5a Remove some debug code 2022-05-15 14:22:12 +08:00
Daniel Povey
6306f24430 Some changes to algorithm; more diagnostics printing 2022-05-15 14:12:23 +08:00
Daniel Povey
67c402a369 Add some debugging/diagnostic code 2022-05-15 13:28:00 +08:00
Guanbo Wang
9630f9a3ba
Update GigaSpeech reults (#364)
* Update decode.py

* Update export.py

* Update results

* Update README.md
2022-05-15 12:57:40 +08:00
Daniel Povey
747960677e Prob. 1st working version of Abel 2022-05-15 10:13:06 +08:00
Fangjun Kuang
f23dd43719
Update results for libri+giga multi dataset setup. (#363)
* Update results for libri+giga multi dataset setup.
2022-05-14 21:45:39 +08:00
Fangjun Kuang
2d7096dfc6
Decode gigaspeech in GitHub actions (#362)
* Add CI for gigaspeech.
2022-05-14 08:53:22 +08:00
Daniel Povey
a1c6bae5d6 Init pruned_transducer_stateless4b as copy of 4 2022-05-13 22:48:17 +08:00
Daniel Povey
993b36e0b8 Merge remote-tracking branch 'upstream/master' into knowledge_base_1b_L2_ng 2022-05-13 22:47:20 +08:00
Fangjun Kuang
0f180b3ce2
Validate that there are no OOV tokens in BPE-based lexicons. (#359)
* Validate that there are no OOV tokens in BPE-based lexicons.

* Typo fixes.
2022-05-13 14:00:35 +08:00
Fangjun Kuang
e30e042c39
Update decoding script for gigaspeech and remove duplicate files. (#361) 2022-05-13 13:03:16 +08:00
Daniel Povey
44f4aa5f66 Try to resolve merge issues etc 2022-05-13 11:32:23 +08:00
Daniel Povey
4f933f5413 Merge changes from knowledge_base_1bfast; fix nheads 4->8 2022-05-13 11:26:18 +08:00
Guanbo Wang
48a6a9a549
GigaSpeech RNN-T experiments (#318)
* Copy RNN-T recipe from librispeech

* flake8

* flake8

* Update params

* gigaspeech decode

* black

* Update results

* syntax highlight

* Update RESULTS.md

* typo
2022-05-13 11:03:26 +08:00
Fangjun Kuang
7b7acdf369
Support --iter in export.py (#360) 2022-05-13 10:51:44 +08:00
Fangjun Kuang
aeb8986e35
Ignore padding frames during RNN-T decoding. (#358)
* Ignore padding frames during RNN-T decoding.

* Fix outdated decoding code.

* Minor fixes.
2022-05-13 07:39:14 +08:00
Daniel Povey
c4c9b8cf80 Change configuration from M to L 2022-05-12 16:10:08 +08:00
Fangjun Kuang
bc284e88e6
Run decode.py in GitHub actions. (#356) 2022-05-10 14:51:34 +08:00