Fangjun Kuang
e334e570d8
Filter utterances with number_tokens > number_feature_frames. ( #604 )
2022-11-12 07:57:58 +08:00
Zengwei Yao
32de2766d5
Refactor getting timestamps in fsa-based decoding ( #660 )
...
* refactor getting timestamps for fsa-based decoding
* fix doc
* fix bug
2022-11-05 22:36:06 +08:00
Zengwei Yao
3600ce1b5f
Apply delay penalty on transducer ( #654 )
...
* add delay penalty
* fix CI
* fix CI
2022-11-04 16:10:09 +08:00
marcoyang
2271c3d396
remove testing file
2022-11-04 12:26:38 +08:00
marcoyang
a2d7095c1c
resolve conflicts
2022-11-04 11:37:42 +08:00
marcoyang
b3c61b85e3
minor fixes
2022-11-04 11:32:09 +08:00
marcoyang
bdaeaae1ae
resolve conflicts
2022-11-04 11:25:10 +08:00
marcoyang
0df597291f
resolve conflict with timestamp feature
2022-11-04 11:17:56 +08:00
Wei Kang
64aed2cdeb
Fix LG log file name ( #657 )
2022-11-03 23:12:35 +08:00
Wei Kang
163d929601
Add fast_beam_search_LG ( #622 )
...
* Add fast_beam_search_LG
* add fast_beam_search_LG to commonly used recipes
* fix ci
* fix ci
* Fix error
2022-11-03 16:29:30 +08:00
marcoyang
f45d9c4383
resolve conflicts
2022-11-03 11:12:49 +08:00
marcoyang
2a52b8c125
update docs
2022-11-03 11:10:21 +08:00
marcoyang1998
e3f218b62b
Update egs/librispeech/ASR/lstm_transducer_stateless2/decode.py
...
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2022-11-02 22:10:23 +08:00
marcoyang
fb45b95c90
minor fixes
2022-11-02 18:11:39 +08:00
marcoyang
9a01b9098d
include previous added decoding method
2022-11-02 18:03:56 +08:00
marcoyang
6c8d1f9ef5
update
2022-11-02 17:48:58 +08:00
marcoyang
babcfd4b68
update author info
2022-11-02 17:27:31 +08:00
marcoyang
0a46a39e24
update decoding commands
2022-11-02 17:25:31 +08:00
marcoyang
86662f0b97
update results
2022-11-02 17:24:53 +08:00
marcoyang
63d0a52dbd
support RNNLM shallow fusion in stateless5
2022-11-02 16:37:29 +08:00
marcoyang
de2f5e3e6d
support RNNLM shallow fusion for LSTM transducer
2022-11-02 16:15:56 +08:00
Wei Kang
d389524d45
remove tail padding for non-streaming models ( #625 )
2022-11-01 11:09:56 +08:00
Zengwei Yao
03668771d7
Get timestamps during decoding ( #598 )
...
* print out timestamps during decoding
* add word-level alignments
* support to compute mean symbol delay with word-level alignments
* print variance of symbol delay
* update doc
* support to compute delay for pruned_transducer_stateless4
* fix bug
* add doc
2022-11-01 10:24:00 +08:00
Fangjun Kuang
7f1c0e07b6
Remove onnx and onnxruntime from requirements.txt ( #640 )
...
* Remove onnx and onnxruntime from requirements.txt
2022-10-31 13:44:40 +08:00
Wei Kang
581d0361cc
Fix type hints for decode.py ( #638 )
...
* Fix type hints for decode.py
* Fix flake8
2022-10-30 16:35:30 +08:00
Nagendra Goel
6709bf1e63
Update train.py ( #635 )
...
Add the missing step to add the arguments to the parser.
2022-10-28 10:23:32 +08:00
ezerhouni
9b671e1c21
Add Shallow fusion in modified_beam_search ( #630 )
...
* Add utility for shallow fusion
* test batch size == 1 without shallow fusion
* Use shallow fusion for modified-beam-search
* Modified beam search with ngram rescoring
* Fix code according to review
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2022-10-21 16:44:56 +08:00
marcoyang1998
c30b8d3a1c
fix number of parameters in RESULTS.md ( #627 )
2022-10-19 16:53:29 +08:00
Fangjun Kuang
d69bb826ed
Support exporting LSTM with projection to ONNX ( #621 )
...
* Support exporting LSTM with projection to ONNX
* Add missing files
* small fixes
2022-10-18 11:25:31 +08:00
Fangjun Kuang
d1f16a04bd
fix type hints for decode.py ( #623 )
2022-10-18 06:56:12 +08:00
Fangjun Kuang
a66e74b92f
Fix links in the doc ( #619 )
2022-10-14 12:23:47 +08:00
Fangjun Kuang
c39cba5191
Support exporting to ONNX for the wenetspeech recipe ( #615 )
...
* Support exporting to ONNX for the wenetspeech recipe
2022-10-13 15:17:20 +08:00
Zengwei Yao
aa58c2ee02
Modify ActivationBalancer for speed ( #612 )
...
* add a probability to apply ActivationBalancer
* minor fix
* minor fix
2022-10-13 15:14:28 +08:00
Fangjun Kuang
1c07d2fb37
Remove all-in-one for onnx export ( #614 )
...
* Remove all-in-one for onnx export
* Exit on error for CI
2022-10-12 10:34:06 +08:00
Yunusemre
f3db4ea871
exporting projection layers of joiner separately for onnx ( #584 )
...
* exporting projection layers of joiner separately for onnx
2022-10-11 18:22:28 +08:00
Zengwei Yao
f3ad32777a
Gradient filter for training lstm model ( #564 )
...
* init files
* add gradient filter module
* refact getting median value
* add cutoff for grad filter
* delete comments
* apply gradient filter in LSTM module, to filter both input and params
* fix typing and refactor
* filter with soft mask
* rename lstm_transducer_stateless2 to lstm_transducer_stateless3
* fix typos, and update RESULTS.md
* minor fix
* fix return typing
* fix typo
2022-09-29 11:15:43 +08:00
LIyong.Guo
923b60a7c6
padding zeros ( #591 )
2022-09-28 21:20:33 +08:00
Fangjun Kuang
099cd3a215
support exporting to ncnn format via PNNX ( #571 )
2022-09-20 22:52:49 +08:00
Fangjun Kuang
97b3fc53aa
Add LSTM for the multi-dataset setup. ( #558 )
...
* Add LSTM for the multi-dataset setup.
* Add results
* fix style issues
* add missing file
2022-09-16 18:40:25 +08:00
Fangjun Kuang
145c44f710
Use modified ctc topo when vocab size is > 500 ( #568 )
2022-09-13 10:59:27 +08:00
Fangjun Kuang
e18fa78c3a
Check that read_manifests_if_cached returns a non-empty dict. ( #555 )
2022-08-28 11:50:11 +08:00
kobenaxie
235eb0746f
fix scaling converter test for decoder(predictor). ( #553 )
2022-08-27 17:26:21 +08:00
marcoyang1998
1e31fbcd7d
Add clamping operation in Eve optimizer for all scalar weights to avoid ( #550 )
...
non stable training in some scenarios. The clamping range is set to (-10,2).
Note that this change may cause unexpected effect if you resume
training from a model that is trained without clamping.
2022-08-25 12:12:50 +08:00
Duo Ma
0967cf5b38
fixed no cut_id error in decode_dataset ( #549 )
...
* fixed import quantization is none
Signed-off-by: shanguanma <nanr9544@gmail.com>
* fixed no cut_id error in decode_dataset
Signed-off-by: shanguanma <nanr9544@gmail.com>
* fixed more than one "#"
Signed-off-by: shanguanma <nanr9544@gmail.com>
* fixed code style
Signed-off-by: shanguanma <nanr9544@gmail.com>
Signed-off-by: shanguanma <nanr9544@gmail.com>
Co-authored-by: shanguanma <nanr9544@gmail.com>
2022-08-25 10:54:21 +08:00
Yuekai Zhang
f9c3d7f92f
fix typo for export jit script ( #544 )
2022-08-23 17:29:42 +08:00
Duo Ma
dbd61a9db3
fixed import quantization is none ( #541 )
...
Signed-off-by: shanguanma <nanr9544@gmail.com>
Signed-off-by: shanguanma <nanr9544@gmail.com>
Co-authored-by: shanguanma <nanr9544@gmail.com>
2022-08-23 10:19:03 +08:00
Fangjun Kuang
0598291ff1
minor fixes to LSTM streaming model ( #537 )
2022-08-20 09:50:50 +08:00
Zengwei Yao
f2f5baf687
Use ScaledLSTM as streaming encoder ( #479 )
...
* add ScaledLSTM
* add RNNEncoderLayer and RNNEncoder classes in lstm.py
* add RNN and Conv2dSubsampling classes in lstm.py
* hardcode bidirectional=False
* link from pruned_transducer_stateless2
* link scaling.py pruned_transducer_stateless2
* copy from pruned_transducer_stateless2
* modify decode.py pretrained.py test_model.py train.py
* copy streaming decoding files from pruned_transducer_stateless2
* modify streaming decoding files
* simplified code in ScaledLSTM
* flat weights after scaling
* pruned2 -> pruned4
* link __init__.py
* fix style
* remove add_model_arguments
* modify .flake8
* fix style
* fix scale value in scaling.py
* add random combiner for training deeper model
* add using proj_size
* add scaling converter for ScaledLSTM
* support jit trace
* add using averaged model in export.py
* modify test_model.py, test if the model can be successfully exported by jit.trace
* modify pretrained.py
* support streaming decoding
* fix model.py
* Add cut_id to recognition results
* Add cut_id to recognition results
* do not pad in Conv subsampling module; add tail padding during decoding.
* update RESULTS.md
* minor fix
* fix doc
* update README.md
* minor change, filter infinite loss
* remove the condition of raise error
* modify type hint for the return value in model.py
* minor change
* modify RESULTS.md
Co-authored-by: pkufool <wkang.pku@gmail.com>
2022-08-19 14:38:45 +08:00
marcoyang1998
c74cec59e9
propagate changes from #525 to other librispeech recipes ( #531 )
...
* propaga changes from #525 to other librispeech recipes
* refactor display_and_save_batch to utils
* fixed typo
* reformat code style
2022-08-17 17:18:15 +08:00
Fangjun Kuang
669401869d
Filter non-finite losses ( #525 )
...
* Filter non-finite losses
* Fixes after review
2022-08-17 12:22:43 +08:00
