Zengwei Yao
a7e142b7ff
Support long audios recognition ( #980 )
...
* support long file transcription
* rename recipe as long_file_recog
* add docs
* support multi-gpu decoding
* style fix
2023-05-19 20:27:55 +08:00
Zengwei Yao
f18b539fbc
Add the upgraded Zipformer model ( #1058 )
...
* add the zipformer codes, copied from branch from_dan_scaled_adam_exp1119
* support model export with torch.jit.script
* update RESULTS.md
* support exporting streaming model with torch.jit.script
* add results of streaming models, with some minor changes
* update README.md
* add CI test
* update k2 version in requirements-ci.txt
* update pyproject.toml
2023-05-19 16:47:59 +08:00
Fangjun Kuang
ae1949ddcc
Support using the latest master from tencent/ncnn ( #1070 )
...
* Support using the latest master from tencent/ncnn
* small fixes
2023-05-18 20:56:58 +08:00
Yifan Yang
562bda91e4
Add adaption recipe for pruned_transducer_stateless7 ( #1059 )
...
* Add mux for finetune
* Add comments
* Fix for black
* Update finetune.py
2023-05-17 16:02:27 +08:00
Wei Kang
bccd20d978
Traning with byte level BPE (TAL_CSASR) ( #1033 )
...
* Add byte level bpe tal_csasr recipe
* Minor fixes to decoding and exporting
* Fix prepare.sh
* Update results
2023-05-16 12:44:52 +08:00
Fangjun Kuang
6c326427a0
Support exporting streaming conformer to ONNX ( #1047 )
2023-05-10 14:47:37 +08:00
Fangjun Kuang
5b50ffda54
support using mini librispeech in training ( #1048 )
...
* support mini librispeech in training
* update onnx export doc
2023-05-09 15:10:06 +08:00
Fangjun Kuang
ebbab37776
Fix broken code in download_lm.py ( #1046 )
2023-05-08 20:48:17 +08:00
Peter Ross
62c9dd9703
make egs/timit work according to the documentation ( #1044 )
...
* prepare.sh: restore working directory after git lfs pull
* set execute permisons on python scripts called by prepare.sh
2023-05-08 19:07:40 +08:00
Fangjun Kuang
efbb577b88
fix compiling HLG ( #1039 )
2023-05-07 16:26:13 +08:00
Yifan Yang
98569b2607
Update RESULTS.md ( #1036 )
...
* Update RESULTS.md
2023-05-06 17:51:55 +08:00
Wei Kang
80156dda09
Training with byte level BPE (AIShell) ( #986 )
...
* copy files from zipformer librispeech
* Add byte bpe training for aishell
* compile LG graph
* Support LG decoding
* Minor fixes
* black
* Minor fixes
* export & fix pretrain.py
* fix black
* Update RESULTS.md
* Fix export.py
2023-05-04 19:16:17 +08:00
Yuanhang Zhang
b0228c536e
Fix typo in librispeech OpenFST-based HLG preparation script ( #1028 )
2023-04-28 19:52:32 +08:00
marcoyang1998
45c13e90e4
RNNLM rescore + Low-order density ratio ( #1017 )
...
* add rnnlm rescore + LODR
* add LODR in decode.py
* update RESULTS
2023-04-24 15:00:02 +08:00
Yifan Yang
2096e69bda
Use CutSet.mux for multidataset ( #1020 )
...
* Use CutSet.mux
* Remove mischange
* Fix for style check
2023-04-23 18:41:44 +08:00
Yifan Yang
d67a49afe4
Add multidataset ( #1010 )
...
* Add Common Voice for multidataset
* Add prepare_multidataset.sh
* Add dataset mixing
* Update prepare_multidataset.sh
* Update prepare_giga_speech.sh
* update comments
* Add split and shuffle mechanism
* Add multi-dataset train
* Fix for deleting
* Fix for modifying
* Add comments
* Change type for perturb_speed
* Fix for style check
* Small fix
* Add filter
* Remove warning
2023-04-21 18:09:41 +08:00
marcoyang1998
57d6482a79
Streaming Zipformer with multi-dataset ( #984 )
...
* modify train.py
* add right padding option in decode.py
* update RESULTS.md
2023-04-21 15:43:28 +08:00
Wei Kang
0efed1cec5
Fix path in aishell rnnlm training ( #1016 )
2023-04-20 23:09:31 +08:00
Wei Kang
5c65516e05
Fix aishell rnnlm training command ( #1015 )
2023-04-20 16:14:16 +08:00
Yifan Yang
81d386ef3e
Add compute_ppl.py and ngram_entropy_pruning.py ( #1013 )
2023-04-20 12:27:43 +08:00
Wen Ding
78b9dcc936
Support exporting BS Zipformer models to ONNX, used in Triton Server ( #1008 )
...
* Support export BS Zipformer models to ONNX in Tritron
* Update copyright
* Update exporting codes for BS zipformer models
* Code format
* Update comments
* Update export_onnx.py
---------
Co-authored-by: Yifan Yang <64255737+yfyeung@users.noreply.github.com>
2023-04-18 17:05:08 +08:00
Yifan Yang
05e7435d0d
Move soft links into proper position ( #1007 )
2023-04-18 10:11:12 +08:00
Yifan Yang
8838fe0bd2
Zipformer for Common Voice ( #997 )
...
* Add soft links in pruned_transducer_stateless7 for CommonVoice
* Add python files
* Update prepare.sh
* Update normalization
* Fix for soft links
* Add some docs
* Add export
* Update egs/commonvoice/ASR/RESULTS.md
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* Add export for onnx
---------
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2023-04-17 17:47:25 +08:00
marcoyang1998
34d1b07c3d
Modified beam search with RNNLM rescoring ( #1002 )
...
* add RNNLM rescore
* add shallow fusion and lm rescore for streaming zipformer
* minor fix
* update RESULTS.md
* fix yesno workflow, change from ubuntu-18.04 to ubuntu-latest
2023-04-17 16:43:00 +08:00
Fangjun Kuang
e32658e620
Fix torch.jit.script() export for streaming zipformer. ( #1005 )
2023-04-17 16:13:30 +08:00
Zengwei Yao
7c7d9ab042
add @torch.jit.export for streaming_forward func in Zipformer class ( #1004 )
2023-04-17 12:03:52 +08:00
Zengwei Yao
5f066d3d53
support decoding and computing RTF on test sets with onnx models ( #995 )
...
* support decode and compute RTF on test sets with onnx models
* support onnx export and decode in pruned_transducer_stateless
2023-04-12 19:04:50 +08:00
Yifan Yang
dbf2aa3212
Create preprocess_commonvoice.py ( #996 )
2023-04-11 21:04:54 +08:00
Yifan Yang
3cb0a0121b
Add Common Voice ( #994 )
...
* Add commonvoice
* Add data preparation recipe
* Updata
* update prepare.sh
* Fix for black
* Update prefix with cv-
* 20 ->
* Update compute_fbank_commonvoice_dev_test.py
* Update prepare.sh
* Update compute_fbank_commonvoice_dev_test.py
2023-04-11 20:56:40 +08:00
Yifan Yang
33578cca48
Fix filter_cuts in compute_fbank_librispeech.py ( #993 )
2023-04-11 11:12:05 +08:00
Yifan Yang
6434c8eadc
Add averaged model && change start from 0 to 1 && fix typo for gigaspeech ( #990 )
...
* Add averaged model && change start from 0 to 1 && fix typo
* Update train.py
* Set use-averaged-model False for BC
---------
Co-authored-by: yifanyang <yifanyeung@yifanyangs-MacBook-Pro.local>
2023-04-09 20:53:47 +08:00
Zengwei Yao
136aa94d57
remove duplicated lines ( #988 )
2023-04-06 17:47:33 +08:00
Yifan Yang
c90f57afdb
Remove simulate streaming from stateless8 ( #985 )
2023-04-04 11:04:00 +08:00
marcoyang1998
d337398d29
Shallow fusion for Aishell ( #954 )
...
* add shallow fusion and LODR for aishell
* update RESULTS
* add save by iterations
2023-04-03 16:20:29 +08:00
Yifan Yang
46bf6df62f
Remove simulate streaming from stateless7 ( #983 )
...
* Remove simulate streaming from stateless7
2023-04-03 14:55:45 +08:00
Yifan Yang
180c7c2b7a
Add UniqueLexicon for gigaspeech ( #982 )
2023-04-03 12:39:34 +08:00
Yifan Yang
12a222aa4b
Fix comments on the usage of train.py ( #981 )
2023-04-02 16:32:43 +08:00
Fangjun Kuang
a632b24c35
Export int8 quantized models for non-streaming Zipformer. ( #977 )
...
* Export int8 quantized models for non-streaming Zipformer.
* Delete export-onnx.py
* Export int8 models for other folders
2023-03-31 22:46:19 +08:00
marcoyang1998
c21b6a208b
Add finetuning script for aishell ( #974 )
...
* add aishell finetune scripts
* add an example bash script
2023-03-30 17:08:46 +08:00
Zengwei Yao
2a5a75cb56
add option of using full attention for streaming model decoding ( #975 )
2023-03-30 14:30:13 +08:00
Zengwei Yao
bcc5923ab9
Support batch-wise forced-alignment ( #970 )
...
* support batch-wise forced-alignment based on beam search
* add length_norm to HypothesisList.topk()
* Use Hypothesis and HypothesisList instead
2023-03-28 23:24:24 +08:00
Fangjun Kuang
35e21a0d2e
Fix torchscript export for aishell ( #969 )
2023-03-27 14:08:26 +08:00
Fangjun Kuang
8c3ea93fc8
Save meta data to exported ONNX models ( #968 )
2023-03-27 11:39:29 +08:00
Zengwei Yao
7155769c19
minor fix, remove numel = p.numel() in optim.py ( #967 )
2023-03-24 15:30:29 +08:00
Peng He
f260a09ed4
remove if-branch at downsample pad in zipformer for onnx-export compatibility ( #965 )
2023-03-24 14:30:43 +08:00
Wei Kang
d74822d07b
Fix wenetspeech decoding speed ( #953 )
2023-03-21 21:35:32 +08:00
marcoyang1998
7948624a22
Support fine-tuning ( #944 )
...
* support finetune
* add files for decoding giga
* support initializing modules
* add a fine-tune bash script
2023-03-17 13:44:29 +08:00
Jason's Lab
6196b4a407
Add char-based language model training process for aishell. ( #945 )
...
* Add char-based language model training process for aishell.
Add soft link from librispeech/ASR/local/sort_lm_training_data.py to aishell/ASR/local/
---------
Co-authored-by: lichao <www.563042811@qq.com>
2023-03-16 09:52:11 +08:00
Yifan Yang
a48812ddb3
Ban the test_rnn.py in ci-test ( #949 )
2023-03-15 22:02:20 +08:00
Yifan Yang
cad6735e07
Modify make_pad_mask to support TensorRT ( #943 )
...
* Modify make_pad_mask to support TensorRT
* Fix for test
2023-03-10 19:28:59 +08:00
