mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 18:12:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
749 Commits 5 Branches 3 Tags
Commit Graph

749 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
ff3f026381
Checkout the LM for aishell explicitly (#642) 2022-10-31 19:47:43 +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
Teo Wen Shen
1abf2863bb
fix typos (#639) 2022-10-30 22:47:21 +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
Fangjun Kuang
499ac24ecb
Install kaldifst for GitHub actions (#632) 
* Install kaldifst for GitHub actions
 2022-10-24 15:07:29 +08:00
Fangjun Kuang
348494888d
Add kaldifst to requirements.txt (#631) 2022-10-22 13:14:44 +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
Teo Wen Shen
15c1a4a441
CSJ Data Preparation (#617) 
* workspace setup

* csj prepare done

* Change compute_fbank_musan.py t soft link

* add description

* change lhotse prepare csj command

* split train-dev here

* Add header

* remove debug

* save manifest_statistics

* generate transcript in Lhotse

* update comments in config file
 2022-10-18 15:56:43 +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
11bff57586
Add doc about model export (#618) 
* Add doc about model export

* fix typos
 2022-10-14 10:16:34 +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
KajiMaCN
0019463c83
update docs (#611) 
* update docs

Co-authored-by: unknown <mazhihao@jshcbd.cn>
Co-authored-by: KajiMaCN <moonlightshadowmzh@gmail.com>
 2022-10-11 13:24:59 +08:00
Fangjun Kuang
3614d7ff6d
Add dill to requirements.txt (#613) 
* Add dill to requirements.txt

* Disable style check for python 3.7
 2022-10-10 22:50:25 +08:00
shcxlee
bf2c4a488e
Modified train.py of tedlium3 models (#597) 2022-10-02 13:01:15 +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
3b5846effa
Update kaldifeat in CI tests (#583) 2022-09-28 20:51:06 +08:00
Fangjun Kuang
9ae2f3a3c5
Small fixes to the transducer training doc (#575) 2022-09-21 14:20:49 +08:00
Fangjun Kuang
099cd3a215
support exporting to ncnn format via PNNX (#571) 2022-09-20 22:52:49 +08:00
Teo Wen Shen
436942211c
Adding Dockerfile for Ubuntu18.04-pytorch1.12.1-cuda11.3-cudnn8 (#572) 
* Changed Dockerfile

* Update Dockerfile

* Dockerfile

* Update README.md

* Add Dockerfiles

* Update README.md

Removed misleading CUDA version, as the Ubuntu18.04-pytorch1.7.1-cuda11.0-cudnn8 Dockerfile can only support CUDA versions >11.0.
 2022-09-20 10:52:24 +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
shcxlee
9e24642faf
Modified prepare_transcripts.py and preprare_lexicon.py of tedlium3 recipe (#567) 2022-09-10 10:32:49 +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
Fangjun Kuang
d68b8e9120
Disable CUDA_LAUNCH_BLOCKING in wenetspeech recipes. (#554) 
* Disable CUDA_LAUNCH_BLOCKING in wenetspeech recipes.

* minor fixes
 2022-08-28 11:17:38 +08:00
kobenaxie
235eb0746f
fix scaling converter test for decoder(predictor). (#553) 2022-08-27 17:26:21 +08:00
rickychanhoyin
2636a3dd58
minor changes for correct path names && import module text2segments.py (#552) 
* Update asr_datamodule.py

minor file names correction

* minor changes for correct path names && import module text2segments.py
 2022-08-27 17:23:45 +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
rxhmdia
626a26fc2a
some small changes for aidatatang_200zh (#542) 
* Update prepare.sh

* Update compute_fbank_aidatatang_200zh.py
 2022-08-23 17:30:03 +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
Zengwei Yao
c0101185d7
consider case of empty tensor (#540) 2022-08-22 21:42:56 +08:00
Lucky Wong
9277c95bcd
Pruned transducer stateless2 for AISHELL-1 (#536) 
* Fix not enough values to unpack error .

* [WIP] Pruned transducer stateless2 for AISHELL-1

* fix the style issue

* code format for black

* add pruned-transducer-stateless2 results for AISHELL-1

* simplify result
 2022-08-22 10:17:26 +08:00
Fangjun Kuang
0598291ff1
minor fixes to LSTM streaming model (#537) 2022-08-20 09:50:50 +08:00
rickychanhoyin
cdea2d26d4
Update asr_datamodule.py (#538) 
minor file names correction
 2022-08-20 00:16:38 +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
Lucky Wong
31686ac829
Fix not enough values to unpack error . (#533) 2022-08-18 10:45:06 +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