Daniel Povey
77357cdaa8
Change scale from 0.1 to 0.05
2022-06-10 12:42:43 +08:00
Daniel Povey
173c8e6ca3
Make decorrelate scale really 0.1
2022-06-10 12:39:01 +08:00
Fangjun Kuang
9f6c748b30
Add links to sherpa. ( #417 )
...
* Add links to sherpa.
2022-06-10 12:19:18 +08:00
Fangjun Kuang
bfeab319c9
Fix aishell. ( #416 )
2022-06-10 11:47:43 +08:00
Daniel Povey
42667aacf9
Remove linear layers from RandomCombine
2022-06-10 11:38:50 +08:00
Daniel Povey
c92d9d72aa
Fix inf issue
2022-06-10 11:20:47 +08:00
Daniel Povey
950cd4a3e8
Introduce normalization..
2022-06-10 10:47:18 +08:00
Daniel Povey
e891a65735
Move Decorrelate module to after encoder, with scale 0.02->0.1
2022-06-10 10:15:28 +08:00
Daniel Povey
4a5143e548
Increase decay to 1k
2022-06-10 10:09:46 +08:00
Daniel Povey
e2ef8732d1
Increase beta to 0.95
2022-06-10 10:05:28 +08:00
Daniel Povey
a61e21ac85
Change beta to 0.9
2022-06-09 23:33:05 +08:00
Daniel Povey
2c5ebc065e
Change eps to 1e-20
2022-06-09 23:24:33 +08:00
Daniel Povey
c533f91fa2
Remove one line..
2022-06-09 23:13:16 +08:00
Daniel Povey
0fd2cb141f
Code cleanup and refactoring
2022-06-09 22:54:56 +08:00
Daniel Povey
2621cb7f54
Change beta to 0.8
2022-06-09 20:17:12 +08:00
Daniel Povey
082a890635
Fix apply_prob_decay to 500
2022-06-09 19:20:03 +08:00
Daniel Povey
fca844d80c
Make it really have 2k decay and revert to 0.02 scale
2022-06-09 17:45:11 +08:00
Daniel Povey
e99344f15e
Increase scale to 0.04
2022-06-09 13:24:31 +08:00
Daniel Povey
bfcd288afd
Decrease scale on decorrelate component from 0.02 to 0.01
2022-06-09 12:07:19 +08:00
Daniel Povey
56d6dd55ae
Bug fixes
2022-06-09 12:06:35 +08:00
Fangjun Kuang
dbda1644b5
Replace load_manifest_lazy with load_manifest for MUSAN. ( #412 )
2022-06-09 11:42:18 +08:00
Daniel Povey
1669e21c0c
Use decorrelation in conformer layers also
2022-06-09 11:31:52 +08:00
Fangjun Kuang
ed66877694
Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. ( #411 )
2022-06-09 11:18:52 +08:00
Daniel Povey
b9a476c7bb
Remove loss factor from decorr_loss_scale
2022-06-08 20:19:17 +08:00
Quandwang
8512aaf585
fix typos ( #409 )
2022-06-08 20:08:44 +08:00
Daniel Povey
8e56445c70
Try to resolve graph-freed problem
2022-06-08 20:07:35 +08:00
Daniel Povey
46ca1cd4c4
Add Decorrelate module that adds something to gradients in backward pass
2022-06-08 19:44:58 +08:00
Daniel Povey
9fb8645168
Implement JoinDropout
2022-06-08 16:17:42 +08:00
Mingshuang Luo
5079d99ee2
a correction for text2segmentation.py ( #407 )
2022-06-08 12:06:57 +08:00
Daniel Povey
e7886d49a9
Bug fix
2022-06-08 11:05:29 +08:00
Daniel Povey
a83bde1372
Simplify implementation as current idea was not working to decorrelate
2022-06-08 10:24:41 +08:00
Daniel Povey
135be1e19c
Change dropout_rate from 0.2 to 0.1; fix logging statement; fix assignment to rand_scales, nonrand_scales to use [:]
2022-06-08 00:42:04 +08:00
Daniel Povey
a6050cb2de
Implement new, more principled but maybe slower version.
2022-06-07 23:38:38 +08:00
Daniel Povey
75c822c7e9
Pre and post-multiply by inv_sqrt_stddev,stddev
2022-06-07 20:32:18 +08:00
Daniel Povey
a270973b69
Add gaussian version of decorrelation
2022-06-07 18:55:48 +08:00
Daniel Povey
5d24489752
Have 2 scales on dropout
2022-06-07 18:31:42 +08:00
Fangjun Kuang
1094a3cb37
Replace LilcomChunkyWriter with ChunkedLilcomHdf5Writer. ( #404 )
2022-06-07 18:14:25 +08:00
Daniel Povey
53ca61db7a
Reduce scale on decorrelation by 5, to 0.01
2022-06-07 17:10:54 +08:00
Daniel Povey
7c6d923d3f
Add decorrelation to joiner
2022-06-07 16:47:54 +08:00
Daniel Povey
cd6b707e2b
Various bug fixes
2022-06-07 16:45:32 +08:00
Daniel Povey
40a0934b4e
Implement GaussProjDrop
2022-06-07 11:51:24 +08:00
Fangjun Kuang
80c46f0abd
Fix exporting emformer with torchscript using torch 1.6.0 ( #402 )
2022-06-07 09:19:37 +08:00
Daniel Povey
4352a16f57
Fix bug that relates to modifying U in place
2022-06-06 17:43:15 +08:00
Fangjun Kuang
29fa878fff
Fix Emformer for torchscript using torch 1.6.0 ( #401 )
2022-06-06 17:08:07 +08:00
Daniel Povey
31848dcd11
Randomize the projections
2022-06-06 16:07:28 +08:00
Mingshuang Luo
0a21eaae7f
do a change for decode.py ( #400 )
2022-06-06 15:44:04 +08:00
Daniel Povey
6fdb356315
Bug fix RE GPU device
2022-06-06 15:40:20 +08:00
Daniel Povey
71e927411a
Implement FixedProjDrop
2022-06-06 15:38:59 +08:00
Fangjun Kuang
f1abce72f8
Use jsonl for CutSet in the LibriSpeech recipe. ( #397 )
...
* Use jsonl for cutsets in the librispeech recipe.
* Use lazy cutset for all recipes.
* More fixes to use lazy CutSet.
* Remove force=True from logging to support Python < 3.8
* Minor fixes.
* Fix style issues.
2022-06-06 10:19:16 +08:00
Daniel Povey
28df3ba43f
Fix bug re half precision
2022-06-05 23:26:59 +08:00
