mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-08 00:24:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
218 Commits 5 Branches 3 Tags
Commit Graph

171 Commits

Author SHA1 Message Date
yaozengwei
24db3a1934 update emformer_pruned_transducer_stateless/emformer.py 2022-04-20 14:21:45 +08:00
yaozengwei
42f8afd264 Merge branch 'streaming_decoding' into streaming 2022-04-20 11:10:53 +08:00
yaozengwei
e74654c2a2 Formatted imports. 2022-04-19 22:05:14 +08:00
yaozengwei
5228b44de7 Support modified beam search decoding for streaming inference with Emformer model. 2022-04-19 22:00:47 +08:00
yaozengwei
328ad280a4 Support state stacking and unstacking operations for emformer_pruned_transducer_stateless/emformer.py 2022-04-19 17:58:51 +08:00
yaozengwei
b343cb51dc Merge remote-tracking branch 'k2-fsa/streaming' into streaming_new 2022-04-18 14:48:36 +08:00
Fangjun Kuang
0f45356ee6
Add streaming feature extractor. (#302) 
* Add streaming feature extractor.

* Parallel streaming decode with greedy search.

* Fix typos.

* Use torch.stack() to replace torch.cat()
 2022-04-18 10:38:56 +08:00
yaozengwei
df7919f4bf update test functions for conv_emformer_transducer/emformer.py 2022-04-14 19:16:30 +08:00
yaozengwei
32420cc3e4 Add test functions for torchaudio emformer codes. 2022-04-14 17:07:47 +08:00
yaozengwei
524f3aa015 update test functions for emformer. 2022-04-14 16:41:52 +08:00
yaozengwei
4130892971 delete duplicated dropout in emformer attention and update emformer test codes. 2022-04-13 23:46:42 +08:00
yaozengwei
c2808f8541 Support cache of left context for causal convolution. 2022-04-12 20:13:51 +08:00
yaozengwei
651745b220 minor fix doc in emformer.py 2022-04-11 12:42:47 +08:00
yaozengwei
6c1f9b5181 Add wenet ref in ConvolutionModule class. 2022-04-11 12:38:45 +08:00
yaozengwei
1d74c5e596 Support causal convolution in emformer encoder layer. 2022-04-11 12:28:15 +08:00
Fangjun Kuang
7f73043219 Merge remote-tracking branch 'dan/master' into streaming 2022-04-10 23:25:56 +08:00
yaozengwei
a24eef8096 update conv_emformer_transducer/emformer.py. 2022-04-10 20:29:22 +08:00
yaozengwei
8129470586 first upload the conv_emformer_transducer recipe, integrating convolution module into emformer layers. 2022-04-10 20:24:20 +08:00
yaozengwei
3e131891a2 update test_emformer.py 2022-04-08 20:43:54 +08:00
yaozengwei
d58002c414 update emformer.py 2022-04-08 20:31:32 +08:00
Fangjun Kuang
78b8792d1d
Fix potential bugs in PyTorch that exist in label_smoothing. (#300) 2022-04-08 13:41:33 +08:00
yaozengwei
2d1b90f758 update the docs of Emformer class in emformer.py 2022-04-08 10:59:39 +08:00
yaozengwei
374eacdd5c First upload emformer_pruned_transducer_stateless recipe, refator emformer codes from torchaudio. 2022-04-07 21:32:59 +08:00
yaozengwei
9423b3899f Update emformer_pruned_transducer_stateless/emformer.py and upload emformer_pruned_transducer_stateless/test_emformer.py. 2022-04-05 22:28:46 +08:00
yaozengwei
fe43c1349e First upload emformer_pruned_transducer_stateless/emformer.py, modified from torchaudio. 2022-04-05 22:28:46 +08:00
yaozengwei
b0bce20e21 Modify subsampling.py to make T'=T//4 strictly 2022-04-05 22:28:46 +08:00
Wei Kang
cb3ba16f2b
Fix aishell prepare.sh when using pre-download data (#291) 2022-04-05 10:22:49 +08:00
Fangjun Kuang
87cf9231ea
Support specifying iteration number of checkpoints for decoding. (#289) 2022-04-03 13:02:08 +08:00
Fangjun Kuang
189ca555b1
Use Emformer as RNN-T encoder. (#278) 
* Add emformer model.

* Copy files.

* Use Emformer model as RNN-T encoder.

* Support streaming decoding.

* Minor fixes.

* Add RNN-T Emformer for Aishell.
 2022-04-02 13:37:39 +08:00
Fangjun Kuang
e7493ede90
Don't use a lambda for dataloader's worker_init_fn. (#284) 
* Don't use a lambda for dataloader's worker_init_fn.
 2022-03-31 20:32:00 +08:00
Fangjun Kuang
9a11808ed3
Set the seed for dataloader. (#282) 
Also, suppress torch warnings about division by truncation.
 2022-03-31 16:48:46 +08:00
Fangjun Kuang
395a3f952b
Batch decoding for models trained with optimized_transducer (#267) 
* Add greedy search in batch mode.
* Add modified beam search in batch mode.
 2022-03-23 19:11:34 +08:00
Fangjun Kuang
3ae7265737
More fixes to the checkpoint code. (#266) 2022-03-23 14:37:54 +08:00
Fangjun Kuang
6a091da0b0
Minor fixes for saving checkpoints. (#265) 
* Minor fixes for saving checkpoints.

* Fix loading checkpoints saved by previous code.
 2022-03-23 12:22:05 +08:00
Fangjun Kuang
8c7995d493
Support modified beam search in batch mode. (#264) 
* Support modified beam search in batch mode.
* Update k2 versions in GitHub CI.
 2022-03-22 15:14:04 +08:00
Fangjun Kuang
d5c78a2238
Implement greedy search in batch mode for transducer decoding. (#262) 2022-03-22 10:32:22 +08:00
Wei Kang
b2b4d9e0b6
Add fast beam search decoding (#250) 
* Add fast beam search decoding

* Minor fixes

* Minor fixes

* Minor fixes

* Fix comments

* Fix comments
 2022-03-21 16:22:25 +08:00
Fangjun Kuang
ae564f91e6
Periodically saving checkpoint after processing given number of batches (#259) 
* Periodically saving checkpoint after processing given number of batches.
 2022-03-20 23:51:33 +08:00
Fangjun Kuang
910e6c9306
Minor fixes to tedlimu3 to make ./prepare.sh working. (#258) 2022-03-20 20:26:03 +08:00
Mingshuang Luo
ad28c8c5eb
Tedlium3 transducer stateless (#233) 
* add tedlium3 transducer-stateless
 2022-03-18 11:39:06 +08:00
Mingshuang Luo
d0d806560f
Change for asr_datamodule.py (#241) 
* change for asr_datamodule.py

* fix style check

* do a fix
 2022-03-14 00:30:58 +08:00
Fangjun Kuang
bb7f6ed6b7
Add modified beam search for pruned rnn-t. (#248) 
* Add modified beam search for pruned rnn-t.

* Fix style issues.

* Update RESULTS.md.

* Fix typos.

* Minor fixes.

* Test the pre-trained model using GitHub actions.

* Let the user install optimized_transducer on her own.

* Fix errors in GitHub CI.
 2022-03-12 16:16:55 +08:00
Fangjun Kuang
2f4e71f433
Add force alignment for stateless transducer. (#239) 
* Add force alignment for stateless transducer.

* Add more documentation.

* Compute word starting time from framewise token alignment.

* Update README to include force alignment information.

* Fix typos.

* Fix more typos.

* Fixes after review.
 2022-03-12 16:16:15 +08:00
Fangjun Kuang
1603744469
Refactor conformer. (#237) 2022-03-05 19:26:06 +08:00
yaozengwei
ad62981765
Add diagnostics (#230) 
* Adding diagnostics code...

* Move diagnostics code from local dir to the shared icefall dir

* Remove the diagnostics code in the local dir

* Update docs of arguments, and remove stats_types() function in TensorDiagnosticOptions object.

* Update docs of arguments.

* Add copyright information.

* Corrected the time in copyright information.

Co-authored-by: Daniel Povey <dpovey@gmail.com>
 2022-03-04 15:38:23 +08:00
Fangjun Kuang
2f0fbf430c
Remove duplicate files. (#236) 2022-03-04 11:56:31 +08:00
Fangjun Kuang
3ec219dfa0
Add stateless transducer tutorial. (#235) 
* WIP: Add stateless transducer tutorial.

* Add more doc.

* Minor fixes.
 2022-03-03 22:33:47 +08:00
Fangjun Kuang
1ff6196c44
Fix joiner (#234) 
* Add tests for Joiner

* Remove duplicate files.
 2022-03-02 16:41:14 +08:00
Fangjun Kuang
50d2281524
Add modified transducer loss for AIShell dataset (#219) 
* Add modified transducer for aishell.

* Minor fixes.

* Add extra data in transducer training.

The extra data is from http://www.openslr.org/62/

* Update export.py and pretrained.py

* Update CI to install pretrained models with aishell.

* Update results.

* Update results.

* Update README.

* Use symlinks to avoid copies.
 2022-03-02 16:02:38 +08:00
Fangjun Kuang
05cb297858
Update result for full libri + GigaSpeech using transducer_stateless. (#231) 2022-03-01 17:01:46 +08:00