Daniel Povey
a5b9b7b974
Cosmetic changes
2022-08-05 03:51:00 +08:00
Yunusemre
7157f62af3
Merging onnx models ( #518 )
...
* add export function of onnx-all-in-one to export.py
* add onnx_check script for all-in-one onnx model
* minor fix
* remove unused arguments
* add onnx-all-in-one test
* fix style
* fix style
* fix requirements
* fix input/output names
* fix installing onnx_graphsurgeon
* fix instaliing onnx_graphsurgeon
* revert to previous requirements.txt
* fix minor
2022-08-04 23:03:41 +08:00
Zengwei Yao
a4dd273776
fix about tensorboard ( #516 )
...
* fix metricstracker
* fix style
2022-08-04 19:57:12 +08:00
Mingshuang Luo
e538232485
change for pruned rnnt5 train.py ( #519 )
2022-08-04 12:29:39 +08:00
Daniel Povey
dc9133227f
Reworked how inverse is done, fixed bug in _apply_min_max_with_metric, regarding how M is normalized.
2022-08-04 09:46:14 +08:00
Weiji Zhuang
36eacaccb2
Fix preparing char based lang and add multiprocessing for wenetspeech text segmentation ( #513 )
...
* add multiprocessing for wenetspeech text segmentation
* Fix preparing char based lang for wenetspeech
* fix style
Co-authored-by: WeijiZhuang <zhuangweiji@xiaomi.com>
2022-08-03 19:19:40 +08:00
Fangjun Kuang
6af5a82d8f
Convert ScaledEmbedding to nn.Embedding for inference. ( #517 )
...
* Convert ScaledEmbedding to nn.Embedding for inference.
* Fix CI style issues.
2022-08-03 15:34:55 +08:00
Fangjun Kuang
58a96e5b68
Support exporting to ONNX format ( #501 )
...
* WIP: Support exporting to ONNX format
* Minor fixes.
* Combine encoder/decoder/joiner into a single file.
* Revert merging three onnx models into a single one.
It's quite time consuming to extract a sub-graph from the combined
model. For instance, it takes more than one hour to extract
the encoder model.
* Update CI to test ONNX models.
* Decode with exported models.
* Fix typos.
* Add more doc.
* Remove ncnn as it is not fully tested yet.
* Fix as_strided for streaming conformer.
2022-08-03 10:30:28 +08:00
Daniel Povey
766bf69a98
Reduce cov_max[2] from 4.0 to 3.5
2022-08-03 04:10:11 +08:00
LIyong.Guo
132132f52a
liear_fst_with_self_loops ( #512 )
2022-08-02 22:28:12 +08:00
Daniel Povey
129b28aa9b
Increase cov_min[2] from 0.05 to 0.1; decrease cov_max[2] from 5.0 to 4.0.
2022-08-02 15:17:24 +08:00
Daniel Povey
202752418a
Increase cov_min[2] from 0.02 to 0.05.
2022-08-02 15:15:41 +08:00
Daniel Povey
e44ab25e99
Bug fix
2022-08-02 14:31:37 +08:00
Daniel Povey
e9f4ada1c0
Swap the order of applying min and max in smoothing operations
2022-08-02 11:55:43 +08:00
Daniel Povey
9473c7e23d
Lots of changes to how min and max are applied, use 1-norm for min in smooth_cov but not _apply_min_max_with_metric.
2022-08-02 11:29:54 +08:00
Daniel Povey
6ab4cf615d
1st draft of new method of normalizing covs that uses normalization w.r.t. spectral 2-norm
2022-08-02 09:34:37 +08:00
Daniel Povey
4919134a94
Merge making hidden_dim an arg
2022-08-02 09:09:29 +08:00
Daniel Povey
c64bd5ebcd
Merge making hidden_dim an arg
2022-08-02 09:07:36 +08:00
Daniel Povey
b008340d83
Merge making hidden_dim an arg
2022-08-02 09:01:19 +08:00
Daniel Povey
9f2229edb5
Merge making hidden_dim an arg
2022-08-02 08:58:00 +08:00
Daniel Povey
a45f820e25
Merge making hidden_dim an arg
2022-08-02 08:56:36 +08:00
Daniel Povey
6714f85cc4
Merge making hidden_dim an arg
2022-08-02 08:55:27 +08:00
Daniel Povey
804f264ffd
Merge hidden_dim providing it as arg
2022-08-02 08:40:13 +08:00
Daniel Povey
ee311247ea
Decrease debugging freq
2022-08-01 03:55:18 +08:00
Daniel Povey
4c5d49c448
Some numerical improvements, and a fix to calculation of mean_eig in _apply_min_max_with_metric(), to average over blocks too.
2022-08-01 03:51:39 +08:00
Daniel Povey
e2cc09a8c6
Fix issue with max_eig formula; restore cov_min[1]=0.0025.
2022-07-31 18:29:44 +08:00
Daniel Povey
3590c2fc42
Set cov_min[1] to 0 to stop an invertibility problem
2022-07-31 18:06:01 +08:00
Daniel Povey
7231c610e8
Restore min_cov applied with G.
2022-07-31 02:22:07 -07:00
Daniel Povey
d84a2e22e3
Applying max to G with noinv method with metric.
2022-07-31 02:10:27 -07:00
Daniel Povey
2042c9862c
Merge branch 'pradam_exp1m4_nophase1_noinv' into pradam_exp1m4_nophase1_rework_noinv
2022-07-31 01:32:36 -07:00
Daniel Povey
90fa8a63eb
Use different approach for applying max eig, with matmul, no inverse.
2022-07-31 01:32:11 -07:00
Daniel Povey
ed1a147ef1
Implement no-inverse max-cov
2022-07-31 00:08:02 -07:00
Daniel Povey
0666789cb8
Small numerical improvements; config change of eps and G_diag changed 1.01 to 1.005; decrease an eps from 1e-10 to 1e-20
2022-07-30 21:48:54 -07:00
Daniel Povey
cb67540cdc
this version not working great
2022-07-30 21:14:03 -07:00
Daniel Povey
790e8c4ba9
Changes that should not really affect the results, just cleanup.
2022-07-30 19:20:36 -07:00
Daniel Povey
5184ac570d
Removing phase1, adding regular smoothing with the mean.
2022-07-30 19:15:51 -07:00
Daniel Povey
e1182da6ac
Restoring min_abs and max_abs defaults for the linear_pos proj.
2022-07-31 05:07:50 +08:00
Daniel Povey
105d49d31b
Big simplification to update rule
2022-07-30 00:21:12 -07:00
Daniel Povey
a80a8abf0c
Merge branch 'pradam_exp1l3' into pradam_exp1m3
2022-07-30 09:07:05 +08:00
Daniel Povey
4d5323d6a3
Change cov_min to intermediate value, not seeing clear diffs from changing it
2022-07-30 09:06:23 +08:00
Daniel Povey
c0e652ea87
Fix code, was smoothing in wrong basis.
2022-07-30 09:01:11 +08:00
Daniel Povey
c5a037b8bc
Merge branch 'pradam_exp1l3' into pradam_exp1m3
2022-07-30 08:21:28 +08:00
Daniel Povey
17bc002e6e
Refactoring that does not affect results.
2022-07-30 07:45:29 +08:00
Daniel Povey
3110138ab5
Smooth grad_cov with eps; add a 4th stage of smoothing, this time on Z_inv.
2022-07-30 07:30:32 +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
Daniel Povey
ca28f46f75
Merge branch 'pradam_exp1l2' into pradam_exp1m2
2022-07-29 15:16:10 +08:00
Daniel Povey
3ad042444e
More changes to reduce numerical roundoff for dims with zero grad and params.
2022-07-29 14:38:50 +08:00
Mingshuang Luo
1b478d3ac3
Add other decoding methods (nbest, nbest oracle, nbest LG) for wenetspeech pruned rnnt2 ( #482 )
...
* add other decoding methods for wenetspeech
* changes for RESULTS.md
* add ngram-lm-scale=0.35 results
* set ngram-lm-scale=0.35 as default
* Update README.md
* add nbest-scale for flie name
2022-07-29 12:03:08 +08:00
Daniel Povey
a55f8c9c14
Modify scaling.py to prevent constant values
2022-07-29 11:38:05 +08:00
Lucky Wong
34b4356bad
correction for get rank id. ( #507 )
...
* Fix no attribute 'data' error.
* minor fixes
* correction for get rank id.
2022-07-29 11:28:52 +08:00
