Daniel Povey
a1ae2f8fa9
Revert some accidental changes
2022-06-05 11:40:55 +08:00
Daniel Povey
d6e65a0e7f
Remove decompose=True
2022-06-03 11:48:45 +08:00
Daniel Povey
c7cf229f56
Revers pruned_transducer_stateless4 to upstream/master
2022-05-31 12:45:51 +08:00
Daniel Povey
7011956c6c
Merge remote-tracking branch 'upstream/master' into cain3d_clean_merge
2022-05-31 12:17:45 +08:00
Daniel Povey
c3df609805
Revert lrate changes
2022-05-30 16:24:40 +08:00
Daniel Povey
b01c09a693
Remove the natural gradient stuff while keeping cosmetic changes.
2022-05-30 11:56:11 +08:00
Daniel Povey
8a96f29a11
Further increase learning rate
2022-05-29 11:13:27 +08:00
Daniel Povey
2b8ea98fc2
Improve documentation; remove unused code.
2022-05-28 19:22:09 +08:00
Daniel Povey
295595d334
Revert the exclusion of dim=500
2022-05-28 17:49:16 +08:00
Daniel Povey
0b645662f9
Increase learning rates.
2022-05-28 12:12:34 +08:00
Daniel Povey
e771472a30
Speed up learning rate schedule.
2022-05-28 11:30:45 +08:00
Daniel Povey
828defb019
Some temp code for loading old state dict
2022-05-28 00:29:47 +08:00
Daniel Povey
d89cb53a3b
Revert max_eff_lr to initial_lr
2022-05-27 21:42:20 +08:00
Daniel Povey
7aa47408af
Bug fixes to avoid inf alpha
2022-05-27 21:41:05 +08:00
Daniel Povey
0787583580
Increase max_eff_lr
2022-05-27 21:03:08 +08:00
Daniel Povey
fd0e9d4bad
Fix bug for scalars.
2022-05-27 20:48:41 +08:00
Daniel Povey
503b79252f
Add new update and max_eff_lr
2022-05-27 20:44:10 +08:00
Daniel Povey
4efe920401
More consistent use of eps.
2022-05-27 17:41:19 +08:00
Daniel Povey
eed864a3db
Change power from 0.66 to 1.0, like natural gradient.
2022-05-27 16:45:42 +08:00
Daniel Povey
89fad8cc5a
Change power to 0.66
2022-05-27 16:39:54 +08:00
Daniel Povey
61e7929c60
Remove unused arg
2022-05-26 15:18:03 +08:00
Daniel Povey
8e454bcf9e
Exclude size=500 dim from projection; try to use double for model average
2022-05-26 15:15:27 +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
Daniel Povey
9ef11e64ba
Some small fixes, to bias_correction2 formula and remove bias-u,v-scale
2022-05-22 16:28:33 +08:00
Daniel Povey
b916789ca3
Further increase scales
2022-05-22 12:25:26 +08:00
Daniel Povey
9e206d53fc
Increase initial scale for conv and self_attn
2022-05-22 12:18:57 +08:00
Daniel Povey
56d9928934
Scale down modules at initialization
2022-05-22 11:56:59 +08:00
Daniel Povey
5d57dd3930
Change initial bias scales from 0.1 to 0.2
2022-05-22 10:59:51 +08:00
Daniel Povey
435b073979
Change init of biases to all -0.1..0.1
2022-05-22 10:43:06 +08:00
Daniel Povey
dcab1aee4e
make biases learn faster in a different way.
2022-05-21 17:47:30 +08:00
Daniel Povey
992f922f81
Make biases learn at twice the speed
2022-05-21 17:30:45 +08:00
Daniel Povey
b7adb6d738
Slow down learning of simple_am_proj.weight by 0.5
2022-05-21 17:06:24 +08:00
Daniel Povey
11eac9089e
Fix w.r.t. how cov stats are estimated: storing more stats, and now always zeroing the stats.
2022-05-20 23:05:05 +08:00
Daniel Povey
6f974b32f6
Restore missing factor 1-beta1
2022-05-20 17:43:48 +08:00
Daniel Povey
768c260a4d
Slightly simplify scaling code
2022-05-20 16:43:05 +08:00
Daniel Povey
4257c1024f
Remove initial_speed option
2022-05-20 13:41:56 +08:00
Daniel Povey
abe5abb688
Implement Cain with scdaling incorporated;
...
Removing scaling from ScaledLinear, ScaledConv1d, etc.
2022-05-20 13:36:15 +08:00
Daniel Povey
8fd9e64fdf
Fix eps value
2022-05-19 22:25:18 +08:00
Daniel Povey
1edc0fa841
Fixes to cain
2022-05-19 22:21:41 +08:00
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
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
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
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
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
0989aec741
Replace Eve optimizer with Abel.
2022-05-15 14:33:08 +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
