AI/wekws
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
80 Commits 2 Branches 0 Tags
Commit Graph

43 Commits

Author SHA1 Message Date
Wall.E
51f0fe6dc3
fixed the parameter transfer problem for criterion (#75) 
* fixed the parameter transfer problem for criterion

Co-authored-by: yangyyt <yuntingyang@yuntingdeMacBook-Pro.local>
 2022-07-13 23:50:48 +08:00
胡大炮
141d40704f
[fix bug] add optimizer.zero_grad() in kws/utils/executor.py (#72) (#73) 
* fix bug in kws/utils/executor.py (#72)

* [fix bug] add zero_grad() above backward() in kws/utils/executor.py (#72)
 2022-06-05 22:39:26 +08:00
ryoha
41a3432198
fix export in export_onnx (#71) 2022-05-29 09:30:53 +08:00
Cyan
015748b94e
learning rate won't initiate from 0.001 when continuing training from checkpoint (#67) 
* add .gitattributes

* add long wav

* fix some bugs

* updated lint error

* back the hi_xiaowen/run.sh to the same

* remove the space

* better one

* remove 'num_keyword' parameter

* remove files

* flask8 examine

* override the score and compute_det file

* remove defaultdict

* remove import defaultdict

* learning rate won't initial from 0.001 when continuing training from checkpoint

* fix intent bug with initial learning rate != 0.001
 2022-04-14 16:02:18 +08:00
Cyan
7d142b9528
[examples] refactor FAR computation to support long audio test (#64) 
* add .gitattributes

* add long wav

* fix some bugs

* updated lint error

* back the hi_xiaowen/run.sh to the same

* remove the space

* better one

* remove 'num_keyword' parameter

* remove files

* flask8 examine

* override the score and compute_det file

* remove defaultdict

* remove import defaultdict
 2022-03-24 14:35:07 +08:00
Menglong Xu
ff4b47f94d
[kws] update cross_entropy loss (#62) 
* [kws] update cross_entropy loss

replace nn.CrossEntropyLoss() with F.cross_entropy()

* format
 2022-03-15 19:34:28 +08:00
Binbin Zhang
57021924cb
[kws] support onnx export (#53) 2022-01-15 13:50:34 +08:00
Menglong Xu
f622c55b04
[kws] update parameter for plotting det curve (#54) 2021-12-17 20:52:45 +08:00
Menglong Xu
768900307a
[kws] add code for plotting det curve (#52) 
* [kws] add code for plotting det curve

* format

* format

* format

* format

* [kws] add code for plotting det curve

format

format

format

format

* set xlim and ylim by parameter

* set xlim and ylim optional

* update help information

* update parser type

* Update run.sh
 2021-12-16 18:21:04 +08:00
Binbin Zhang
8943acb51f [kws] put activation in model, so the activation could be exported in script model 2021-12-15 21:10:27 +08:00
Binbin Zhang
f86a797b10
[kws] add static quantize (#44) 
* [kws] add static quantize

* refine lint error in shuffle_list.py

* refine lint

* fix topo
 2021-12-14 14:32:54 +08:00
Binbin Zhang
171309bd9e
[bin] use torchrun to launch ddp training (#42) 2021-12-13 19:45:55 +08:00
Binbin Zhang
28652a766f
[kws] support fuse and quantization (#41) 2021-12-13 19:16:50 +08:00
Menglong Xu
1eda27647b
[fix bug] add sigmoid() in score.py (#37) 
The sigmoid() in kws/model/kws_model.py:KWSModel() was moved into kws/model/loss.py:max_pooling_loss()
To compute the posterior score correctly, the sigmoid() should also be added to kws/bin/score.py:main()
 2021-12-08 13:41:20 +08:00
xiaohou
bd504c3cee
[bin] check torch script (#36) 
* update run.sh

* [network] add code to check whether the model can be exported to torch script or not
 2021-12-07 11:17:47 +08:00
xiaohou
afbc1d2960
[example] add testing code for speech command dataset (#32) 
* update run.sh

* update run.sh

* rename test.py to compute_accuracy.py

* update run,sh
 2021-12-07 10:56:30 +08:00
Binbin Zhang
b55ae111ae
[model] refactor tcn and ds_tcn share the same base class (#35) 2021-12-07 10:52:14 +08:00
Binbin Zhang
c7c5bd3edc
[kws] refine tcn and ds_tcp, add batchnorm (#31) 
* [kws] fix seed type

* [kws] refine tcn and ds_tcn, add batch norm
 2021-12-06 17:24:48 +08:00
xiaohou
37f56db5af
[exampels] add speechcommand train (#30) 
* [example] added code for training speech command dataset

* update kes_model.py

* update kes_model.py

* format

* format

* add more comments to explain the new classifier designed for speech command classification task

* add copyrigh info

* update copyrigh info of classifier.py
 2021-12-06 17:14:33 +08:00
Binbin Zhang
5241491e95
[kws] fix seed type (#26) 2021-12-06 11:38:41 +08:00
Binbin Zhang
a5a54782cc
[kws] use **kvargs for optim to reduce code (#25) 2021-12-06 11:23:44 +08:00
Binbin Zhang
8cfd4ed4f2
[kws] fix weight_decay key error (#23) 2021-12-04 17:19:46 +08:00
Binbin Zhang
dfe8b2536b
Revert "[recipe] suport speech command dataset (#21)" (#22) 
This reverts commit c48c959807e7e80cdd514be9bd019b16e3b816eb.
 2021-12-04 13:55:58 +08:00
xiaohou
c48c959807
[recipe] suport speech command dataset (#21) 
* [recipe] suport speech command dataset

* format

* format

* format

* update run.sh
 2021-12-03 21:07:42 +08:00
jingyong hou
8ea11dc572 fix bug in checking kernel size, kernel size should be a odd number 2021-12-03 10:25:02 +08:00
xiaohou
5236d42800
Update mdtc.py 2021-11-30 17:14:30 +08:00
xiaohou
b9551bb716
Update mdtc.py 2021-11-30 17:07:01 +08:00
xiaohou
8a50252c64
Update mdtc.py 2021-11-30 17:05:48 +08:00
Jingyong Hou
f642c0952a update mdtc.py to prevent possible errors and remove useless functions 2021-11-30 16:47:35 +08:00
lxiao336
ba6919baaf
modifications to get the mdtc model torch-scriptable (#14) 
* modifying some implmentations of mdtc to get the model torch-scripting through

* modifications to get the mdtc model torch-scriptable

Co-authored-by: lxiao336 <shawl336@163.com>
 2021-11-29 11:15:30 +08:00
Binbin Zhang
5bc7c8d64e
Merge pull request #12 from wenet-e2e/dev-jingyonghou 
[fix bug] resolve bugs in score.py
 2021-11-22 09:33:42 +08:00
jingyong hou
a681a8c931 [fix bug] resolve bugs in score.py 2021-11-21 23:20:16 +08:00
jingyong hou
17cd3c47e5 update train.py 2021-11-19 17:18:58 +08:00
jingyong hou
8cd12edfed update loss.py and kws_model.py 2021-11-19 17:14:11 +08:00
jingyong hou
9aaa4fc26c add mannul random seed so we can reproduce the experimental results 2021-11-19 16:23:03 +08:00
jingyong hou
edfc6de743 add results of mdtc 2021-11-19 15:31:11 +08:00
Jingyong Hou
9514336cc4 formatting 2021-11-11 09:57:35 +08:00
Jingyong Hou
603662f152 add a simple intro to MDTC 2021-11-11 09:55:29 +08:00
Jingyong Hou
3326c6d37f formatting 2021-11-11 09:30:37 +08:00
Jingyong Hou
0942092426 format the code 2021-11-10 22:49:53 +08:00
Jingyong Hou
7df9ced666 fixed bug of compute_cmvn_stats.py 2021-11-10 22:40:21 +08:00
Jingyong Hou
4db050eb67 add model mdtc for mobvoi-hotword example 2021-11-10 22:13:46 +08:00
Binbin Zhang
aa0b0c11a8 [kws] add kws base code 2021-11-10 18:48:57 +08:00