mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-10 17:44:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
478 Commits 5 Branches 3 Tags
Commit Graph

387 Commits

Author SHA1 Message Date
Guo Liyong
b3329f333a make export.py call stateless6/train.py instead of stateless2/train.py 2022-05-28 01:21:11 +08:00
LIyong.Guo
9d36a13aa4
Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py 
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
 2022-05-27 15:06:23 +08:00
Guo Liyong
85f35698ef fix type error of dst_manifest_dir 2022-05-27 14:48:11 +08:00
Guo Liyong
50641cdeab Merge branch 'stateless6' of github.com:glynpu/icefall into stateless6 2022-05-27 13:49:39 +08:00
Guo Liyong
973fd83cf1 add intro of statless6 in README 2022-05-27 13:33:22 +08:00
LIyong.Guo
8a4b3497a6
Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py 
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
 2022-05-27 13:08:17 +08:00
Guo Liyong
80dfdd1cfa a short intro to distillation framework 2022-05-27 12:38:45 +08:00
Guo Liyong
f921a7be0e Merge branch 'stateless6' of github.com:glynpu/icefall into stateless6 2022-05-27 12:26:59 +08:00
Guo Liyong
6bc387cf46 check fairseq and quantization 2022-05-27 12:26:43 +08:00
LIyong.Guo
6e1a92ac7c
Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py 
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
 2022-05-27 11:24:30 +08:00
LIyong.Guo
6fff82b917
Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py 
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
 2022-05-27 11:23:43 +08:00
Guo Liyong
91432397cf Merge branch 'stateless6' of github.com:glynpu/icefall into stateless6 2022-05-27 11:04:50 +08:00
Guo Liyong
3f4b7fac84 add results of 100hours 2022-05-27 11:04:28 +08:00
Guo Liyong
c10481a726 fix comment 2022-05-27 10:58:15 +08:00
LIyong.Guo
95e921ce8b
Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py 
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
 2022-05-27 10:54:39 +08:00
Guo Liyong
aa9e287b3a usage 2022-05-27 10:37:29 +08:00
Guo Liyong
d9a6aff863 example usage 2022-05-27 10:28:34 +08:00
Guo Liyong
14a4d1d6f2 fix typo 2022-05-27 09:54:48 +08:00
Guo Liyong
d8f68abff8 distillation with hubert 2022-05-27 09:49:06 +08:00
Guo Liyong
1f37eb5d0c a copy of stateless4 as base 2022-05-26 21:56:43 +08:00
Ewald Enzinger
8c5722de8c
[egs] Add prefix when reading manifests due to recent lhotse changes (#382) 
* [egs] Add prefix when reading manifests due to recent lhotse changes

* Fix wenetspeech

* Fix style issues
 2022-05-23 23:37:35 +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
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
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
Fangjun Kuang
f23dd43719
Update results for libri+giga multi dataset setup. (#363) 
* Update results for libri+giga multi dataset setup.
 2022-05-14 21:45:39 +08:00
Fangjun Kuang
0f180b3ce2
Validate that there are no OOV tokens in BPE-based lexicons. (#359) 
* Validate that there are no OOV tokens in BPE-based lexicons.

* Typo fixes.
 2022-05-13 14:00:35 +08:00
Fangjun Kuang
7b7acdf369
Support --iter in export.py (#360) 2022-05-13 10:51:44 +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
Fangjun Kuang
bc284e88e6
Run decode.py in GitHub actions. (#356) 2022-05-10 14:51:34 +08:00
Zengwei Yao
20f092e709
Support decoding with averaged model when using --iter (#353) 
* support decoding with averaged model when using --iter

* minor fix

* monir fix of copyright date
 2022-05-07 13:09:11 +08:00
Zengwei Yao
c059ef3169
Keep model_avg on cpu (#348) 
* keep model_avg on cpu

* explicitly convert model_avg to cpu

* minor fix

* remove device convertion for model_avg

* modify usage of the model device in train.py

* change model.device to next(model.parameters()).device for decoding

* assert params.start_epoch>0

* assert params.start_epoch>0, params.start_epoch
 2022-05-07 10:42:34 +08:00
Fangjun Kuang
32f05c00e3
Save batch to disk on exception. (#350) 2022-05-06 17:49:40 +08:00
Zengwei Yao
00c48ec1f3
Model average (#344) 
* First upload of model average codes.

* minor fix

* update decode file

* update .flake8

* rename pruned_transducer_stateless3 to pruned_transducer_stateless4

* change epoch number counter starting from 1 instead of 0

* minor fix of pruned_transducer_stateless4/train.py

* refactor the checkpoint.py

* minor fix, update docs, and modify the epoch number to count from 1 in the pruned_transducer_stateless4/decode.py

* update author info

* add docs of the scaling in function average_checkpoints_with_averaged_model
 2022-05-05 21:20:04 +08:00
Fangjun Kuang
8635fb4334
Fix decoding for gigaspeech in the libri + giga setup. (#345) 2022-05-05 20:58:46 +08:00
Fangjun Kuang
e1c3e98980
Save batch to disk on OOM. (#343) 
* Save batch to disk on OOM.

* minor fixes

* Fixes after review.

* Fix style issues.
 2022-05-05 15:09:23 +08:00
Fangjun Kuang
6af15914fa
Validate generated manifest files. (#338) 2022-05-03 07:02:54 +08:00
Fangjun Kuang
6dc2e04462
Update results. (#340) 
* Update results.

* Typo fixes.
 2022-04-29 15:49:45 +08:00
Fangjun Kuang
ac84220de9
Modified conformer with multi datasets (#312) 
* Copy files for editing.

* Use librispeech + gigaspeech with modified conformer.

* Support specifying number of workers for on-the-fly feature extraction.

* Feature extraction code for GigaSpeech.

* Combine XL splits lazily during training.

* Fix warnings in decoding.

* Add decoding code for GigaSpeech.

* Fix decoding the gigaspeech dataset.

We have to use the decoder/joiner networks for the GigaSpeech dataset.

* Disable speed perturbe for XL subset.

* Compute the Nbest oracle WER for RNN-T decoding.

* Minor fixes.

* Minor fixes.

* Add results.

* Update results.

* Update CI.

* Update results.

* Fix style issues.

* Update results.

* Fix style issues.
 2022-04-29 15:40:30 +08:00
Fangjun Kuang
caab6cfd92
Support specifying iteration number of checkpoints for decoding. (#336) 
See also #289
 2022-04-28 14:09:22 +08:00
pehonnet
9a98e6ced6
fix fp16 option in example usage (#332) 2022-04-25 18:51:53 +08:00
whsqkaak
d766dc5aee
Fix some typos. (#329) 2022-04-22 15:54:59 +08:00
Fangjun Kuang
3607c516d6
Update results for torchaudio RNN-T. (#322) 2022-04-20 11:15:10 +08:00
Fangjun Kuang
fce7f3cd9a
Support computing RNN-T loss with torchaudio (#316) 2022-04-19 18:47:13 +08:00
Wei Kang
021c79824e
Add LG decoding (#277) 
* Add LG decoding

* Add log weight pushing

* Minor fixes
 2022-04-19 17:23:46 +08:00
Mingshuang Luo
d88e786513
Changes for pretrained.py (tedlium3 pruned RNN-T) (#311) 2022-04-14 09:54:07 +08:00
Daniel Povey
af6ae840ee Add results for mixed precision with max-duration 300 2022-04-13 20:22:11 +08:00
Guo Liyong
78418ac37c fix comments 2022-04-13 13:09:24 +08:00
Daniel Povey
2a854f5607
Merge pull request #309 from danpovey/update_results 
Update results; will further update this before merge
 2022-04-12 12:22:48 +08:00
Daniel Povey
9ed7a169e1 Add one more epoch of full expt 2022-04-12 12:20:10 +08:00
Daniel Povey
d0a53aad48 Fix tensorboard log location 2022-04-12 11:51:15 +08:00