danfu
3aeed46af2
Merge pull request #5 from kakashidan/zipformer2_streaming
...
small fixes
2023-06-11 23:55:14 +08:00
danqing fu
d84e086798
small fixes
2023-06-11 23:53:24 +08:00
danfu
5d8917066d
Merge pull request #4 from kakashidan/zipformer2_streaming
...
Zipformer2 streaming
2023-06-11 21:42:23 +08:00
danqing fu
15c7035dad
small fixes
2023-06-11 21:39:24 +08:00
danqing fu
d932ed0928
onnx streaming decode
2023-06-11 13:42:16 +08:00
danqing fu
0b63b87092
stream onnx export suc
2023-06-08 13:33:38 +08:00
danqing fu
1378f833bd
small fixes
2023-06-08 10:40:15 +08:00
danqing fu
851bb50cb8
small fixes
2023-06-08 09:47:00 +08:00
danqing fu
4d4188aa81
streaming zipformer onnx export
2023-06-07 21:23:11 +08:00
danfu
a2b8e3545b
Merge pull request #2 from csukuangfj/export_zipformer2_onnx
...
Use torch.jit.script() for position encoding
2023-06-06 15:46:24 +08:00
Fangjun Kuang
26f3049f4c
minor fixes
2023-06-06 15:30:14 +08:00
Fangjun Kuang
9c888b4b66
Merge remote-tracking branch 'kaka/export_zipformer2_onnx' into export_zipformer2_onnx
2023-06-06 15:29:02 +08:00
Fangjun Kuang
97b7e34dc5
small fixes
2023-06-06 15:27:23 +08:00
Fangjun Kuang
d9e7f02225
Use torch.jit.script() for positional encoding
2023-06-06 15:25:11 +08:00
Fangjun Kuang
4cb2395186
Support longer input for the offline model
2023-06-06 14:20:12 +08:00
danqing fu
34c9261f62
minor fixes
2023-06-06 13:12:35 +08:00
danqing fu
acbc4b5808
minor fixes
2023-06-06 11:13:04 +08:00
danqing fu
e609dfee29
minor fixes
2023-06-06 11:12:21 +08:00
danqing fu
09c4946c15
modify max_len to allow longer input audio
2023-06-06 11:09:00 +08:00
danqing fu
8f8b09498f
remove if-branch at downsampling pad
2023-06-06 10:05:59 +08:00
danfu
f59e06c556
Merge pull request #1 from csukuangfj/export_zipformer2_onnx
...
Fix exporting non-streaming zipformer to ONNX via torch.jit.trace()
2023-06-02 14:30:42 +08:00
Fangjun Kuang
7b00b34617
minor fixes
2023-06-02 14:23:47 +08:00
Fangjun Kuang
dd91c89f28
Fix exporting non-streaming zipformer to ONNX via torch.jit.trace()
2023-06-02 14:21:28 +08:00
danqing fu
f43c44236f
add updated zipformer nonstreaming onnx export
2023-06-01 03:36:11 +00:00
Yifan Yang
03853f1ee5
Add peoples_speech ( #1101 )
...
* update
* Small fix
* Update egs/peoples_speech/ASR/prepare.sh
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* limit normalize log
* Update egs/peoples_speech/ASR/local/compute_fbank_peoples_speech_valid_test.py
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
* Update compute_fbank_peoples_speech_splits.py
* Update compute_fbank_peoples_speech_valid_test.py
---------
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2023-05-31 12:46:17 +08:00
Fangjun Kuang
7b0afbdc16
Remove cur_batch_idx ( #1102 )
2023-05-30 14:49:54 +08:00
Fangjun Kuang
1aeffa73bc
remove outdated code in train.py ( #1096 )
2023-05-25 07:47:38 +08:00
Peter Ross
af8907e1ec
Update pre-commit isort package to v5.11.5 ( #1095 )
2023-05-24 19:57:37 +08:00
Zengwei Yao
6826b076d4
add flops profiler, support for Zipformer encoder and Conformer encoder ( #1093 )
...
* add flops profiler, support for Zipformer encoder and Conformer encoder
* support for reworked conformer and old zipformer
* skip black check
2023-05-24 19:10:45 +08:00
Fangjun Kuang
1df71a6b38
add onnx export for stateless2 ( #1086 )
2023-05-23 16:11:00 +08:00
Fangjun Kuang
ea8b15309f
Add onnx export scripts for wenetspeech recipe. ( #1085 )
2023-05-23 13:32:14 +08:00
Fangjun Kuang
dbcf0b41db
Fix stateless7 training error ( #1082 )
2023-05-23 12:52:02 +08:00
marcoyang1998
585e7b224f
Aishell pruned_transducer_stateless7 ( #962 )
...
* Add pruned_transducer_stateless7 for Aishell
* update README.md
* update comments and small fixes
2023-05-23 11:04:33 +08:00
Yifan Yang
7c4ff66a3d
Fix yesno Cl test ( #1078 )
2023-05-22 12:46:43 +08:00
Yifan Yang
90c392b7b3
Add docs for Fine-tune with mux ( #1074 )
...
* Update RESULTS.md
2023-05-22 12:39:51 +08:00
Fangjun Kuang
3883e362ad
Fix yesno CI test ( #1077 )
2023-05-22 12:29:51 +08:00
Zengwei Yao
8070258ec5
fix conv_emformer2, when using right_context_length=0 ( #1076 )
2023-05-21 20:31:54 +08:00
Zengwei Yao
30fcd16c7d
rm zipformer/__init__.py ( #1075 )
2023-05-20 23:12:11 +08:00
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
a5bbfc6f7e
Update doc for exporting to ncnn ( #1072 )
2023-05-19 16:22:08 +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
tomato18463
7a9f40aac5
Update the yesno recipe logs in doc ( #1060 )
2023-05-15 11:16:53 +08:00
arbs-gpu
30bde4b788
fix rnn_lm/train.py usage ( #1055 )
2023-05-11 17:37:47 +08:00
PF Luo
44d016e4a7
export score_token interface for onnx-runtime ( #1050 )
2023-05-10 22:41:07 +08:00
Fangjun Kuang
6c326427a0
Support exporting streaming conformer to ONNX ( #1047 )
2023-05-10 14:47:37 +08:00
Fangjun Kuang
86b0db6eb9
update installation doc ( #1049 )
2023-05-09 16:13:21 +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
