yaozengwei
7f94b86bb0
minor fix doc
2022-06-11 22:44:06 +08:00
yaozengwei
64c9053e39
minor fix
2022-06-11 22:40:40 +08:00
yaozengwei
e011812bab
minor fix doc
2022-06-11 22:31:55 +08:00
yaozengwei
f2974e0df5
fix style
2022-06-11 22:24:12 +08:00
yaozengwei
86b9210d7b
modify doc
2022-06-11 22:22:46 +08:00
yaozengwei
8c03d6079a
minor fix
2022-06-11 22:12:37 +08:00
yaozengwei
ce008aa2ca
delete other test functions
2022-06-11 22:09:53 +08:00
yaozengwei
448a94c00a
add author info
2022-06-11 22:09:16 +08:00
yaozengwei
626a2912ca
modify export.py
2022-06-11 22:03:19 +08:00
yaozengwei
1a9af61497
copy from pruned_transducer_stateless4
2022-06-11 21:40:19 +08:00
yaozengwei
f57f1b8a44
use torch.div
2022-06-11 21:21:49 +08:00
yaozengwei
c8adbcce64
support torch.jit.export
2022-06-11 21:04:30 +08:00
yaozengwei
eadd0f6aa7
Merge remote-tracking branch 'k2-fsa/master' into emformer_conv_scale_new
2022-06-11 18:32:49 +08:00
yaozengwei
f233b16974
add modify_beam_search, fast_beam_search
2022-06-10 22:10:43 +08:00
yaozengwei
026fb22076
fix bugs, no grad, and num_proccessed_frames
2022-06-10 17:17:03 +08:00
Fangjun Kuang
9f6c748b30
Add links to sherpa. ( #417 )
...
* Add links to sherpa.
2022-06-10 12:19:18 +08:00
yaozengwei
507d7c13f4
test states stack and unstack
2022-06-09 22:17:03 +08:00
yaozengwei
7f09720403
refactor streaming decoding
2022-06-09 20:37:16 +08:00
yaozengwei
734d97c47b
remane streaming_feature_extractor.py
2022-06-09 13:05:06 +08:00
yaozengwei
acc8a36b5e
refactor Stream class
2022-06-09 13:00:22 +08:00
Fangjun Kuang
dbda1644b5
Replace load_manifest_lazy with load_manifest for MUSAN. ( #412 )
2022-06-09 11:42:18 +08:00
Fangjun Kuang
ed66877694
Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. ( #411 )
2022-06-09 11:18:52 +08:00
Quandwang
8512aaf585
fix typos ( #409 )
2022-06-08 20:08:44 +08:00
yaozengwei
f8071e9373
modify emformer states stack and unstack, streaming decoding, to be continued
2022-06-07 23:57:20 +08:00
Fangjun Kuang
1094a3cb37
Replace LilcomChunkyWriter with ChunkedLilcomHdf5Writer. ( #404 )
2022-06-07 18:14:25 +08:00
Fangjun Kuang
80c46f0abd
Fix exporting emformer with torchscript using torch 1.6.0 ( #402 )
2022-06-07 09:19:37 +08:00
yaozengwei
5df1406684
copy from streaming branch
2022-06-06 21:51:47 +08:00
yaozengwei
124ad1db8b
copy from streaming branch
2022-06-06 21:20:55 +08:00
yaozengwei
13899dff51
refactor, use fixed-length cache for batch decoding
2022-06-06 21:19:25 +08:00
Fangjun Kuang
29fa878fff
Fix Emformer for torchscript using torch 1.6.0 ( #401 )
2022-06-06 17:08:07 +08:00
Fangjun Kuang
f1abce72f8
Use jsonl for CutSet in the LibriSpeech recipe. ( #397 )
...
* Use jsonl for cutsets in the librispeech recipe.
* Use lazy cutset for all recipes.
* More fixes to use lazy CutSet.
* Remove force=True from logging to support Python < 3.8
* Minor fixes.
* Fix style issues.
2022-06-06 10:19:16 +08:00
Zengwei Yao
148f69d8d9
Update RESULTS.md ( #388 )
...
* update RESULT.md about pruned_transducer_stateless4
* Update RESULT.md
This PR is only to update RESULT.md about pruned_transducer_stateless4.
* set default value of --use-averaged-model to True
* update RESULTS.md and add decode command
* minor fix
* update export.py
* add uploaded files links
* update link
* fix typos
2022-06-04 15:52:35 +08:00
Fangjun Kuang
fbfc98f1d3
Add streaming Emformer stateless RNN-T. ( #390 )
...
* Add streaming Emformer stateless RNN-T.
* Update results for streaming Emformer.
* Minor fixes.
2022-06-01 14:31:47 +08:00
yaozengwei
10998bef69
add tail padding
2022-05-31 18:53:20 +08:00
yaozengwei
7307f1c6bc
fix typos
2022-05-30 22:37:47 +08:00
yaozengwei
603b707fa8
monir style fix
2022-05-28 19:17:19 +08:00
yaozengwei
66b8636878
copy files from existing branch
2022-05-28 18:16:22 +08:00
LIyong.Guo
c4ee2bc0af
[Ready to merge]stateless6: states4 + hubert distillation. ( #387 )
...
* a copy of stateless4 as base
* distillation with hubert
* fix typo
* example usage
* usage
* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* fix comment
* add results of 100hours
* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* check fairseq and quantization
* a short intro to distillation framework
* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* add intro of statless6 in README
* fix type error of dst_manifest_dir
* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* make export.py call stateless6/train.py instead of stateless2/train.py
* update results by stateless6
* adjust results format
* fix typo
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2022-05-28 12:37:50 +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
