speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
4,801 Commits 25 Branches 4 Tags 135 MiB
b166c00722
Commit Graph

4801 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
BienBoy
6ebf6e48eb
fix: resolve CPU runtime error introduced by previous commit (c1e365f) (#2375) 
Fixed a bug that caused a runtime error when running the model on CPU, which was introduced in commit c1e365fea0. The error was related to incorrect handling of device placement.
 2025-02-05 17:47:20 +08:00
BienBoy
c1e365fea0
fix: resolve unexpected 'out of memory' issue in multi-GPU setup (#2373) 
Fixed a bug where calling torch.cuda.empty_cache() caused extra memory usage on 'cuda:0', leading to unexpected 'out of memory' errors in multi-GPU environments.

Reference:
- https://github.com/pytorch/pytorch/issues/25752
- https://github.com/pytorch/pytorch/issues/144025
 2025-02-01 23:29:34 +08:00
游雁
c4e7014492 v1.2.3 2025-01-24 16:59:23 +08:00
游雁
23c6d67288 emotion2vec 2025-01-16 11:25:36 +08:00
takipipo
3530688e0a
Make Emotion2vec support onnx (#2359) 
* Make emotion2vec exportable to onnx

* Make export_meta of emotion2vec consistence with other models

* Include layer norm in the exported onnx model
 2025-01-16 10:33:23 +08:00
游雁
d4f13c2e44 step_or_epoch bugfix 2025-01-10 10:16:11 +08:00
游雁
e6fe602db3 step_or_epoch bugfix 2025-01-10 10:14:30 +08:00
maliubiao
172a3152b4
允许 model.generate 使用bytes io, 以便不写入文件，节省io时间 (#2343) 2024-12-29 22:33:22 +08:00
游雁
a3a1c55c4c v1.2.2 2024-12-25 17:27:10 +08:00
zhifu gao
3f8294b9d7
Revert "shfit to shift (#2266)" (#2336) 
This reverts commit 1367973f98.
 2024-12-25 17:16:11 +08:00
Zhanzhao (Deo) Liang
8c7b7e5feb
fix export_meta import of sense voice (#2334) 2024-12-25 16:40:29 +08:00
Rin Arakaki
1367973f98
shfit to shift (#2266) 2024-12-24 17:51:31 +08:00
majic31
ae7aff2e9c
fix: solve problems in sensevoice_bin.py related to argmax and unique, as mentioned in issue #2331 (#2332) 2024-12-24 17:51:11 +08:00
Dr. Artificial曾小健
2e0b208658
typo fix (#2330) 2024-12-24 13:46:31 +08:00
majic31
23e7ddebcc
Fix the variable name (#2328) 2024-12-24 10:00:14 +08:00
Zhiming Wang
d2cd95bd67
utils.install_model_requirements: support installing with uv (#2329) 
When using the uv[1] package manager, pip commands need to be proxied through
uv's pip compatible interface[2]. Calling pip directly causes a
FileNotFoundError.

[1] https://docs.astral.sh/uv/
[2] https://docs.astral.sh/uv/pip/packages/
 2024-12-24 09:59:37 +08:00
游雁
d32e112894 bug fix 2024-12-23 21:24:55 +08:00
游雁
1e5ef6ed9a bug fix 2024-12-23 19:06:50 +08:00
zhong zhuang
fcb2102a60
Fix seaco onnx export bug (#2325) 2024-12-21 17:14:35 +08:00
Kun Zou
b5ad7c81be
Support eparaformer model on aishell1 recipe (#2327) 2024-12-21 17:13:46 +08:00
shixian
a62cd7a3fd update sensevoice onnx 2024-12-20 10:50:51 +08:00
inisis
1368a9bca4
update README (#2316) 
* update README

* refactor doc
 2024-12-19 13:55:17 +08:00
zhifu gao
f921a71818
Update demo.py 2024-12-17 17:50:39 +08:00
inisis
c4412495bd
add onnxslim reference (#2314) 2024-12-17 12:40:04 +08:00
游雁
9c0d7bee93 Merge branch 'main' of github.com:alibaba-damo-academy/FunASR 
merge
 2024-12-17 11:16:16 +08:00
游雁
fdafd3f6bc emotion2vec 2024-12-17 11:15:53 +08:00
Legend
5e7a8d1cca
Update readme_zh.md (#2312) 2024-12-15 01:47:12 +08:00
Haitao
7263fb08e9
识别结果中有英语时，缺少空格或者第一个单词的问题 (#2284) 
* Update ct-transformer-online.cpp

修复最后两个单词之间没有空格的问题

* Update ct-transformer-online.cpp

解决语音中连续两句英语，offline结果丢失第二句第一个单词的情况。
 2024-12-13 13:47:15 +08:00
游雁
2139ef696b v1.2.0 2024-12-12 11:37:59 +08:00
游雁
5f48457cf1 v1.1.18 2024-12-12 11:37:23 +08:00
游雁
41785b1daf v1.1.18 2024-12-12 11:35:27 +08:00
游雁
bb0017a686 bugfix 2024-12-12 11:35:06 +08:00
游雁
0f3d2d1266 v1.1.17 2024-12-11 14:21:57 +08:00
游雁
92586a4a90 fix bytes 2024-12-10 17:43:58 +08:00
Shi Xian
22b928dd3f
Merge pull request #2269 from modelscope/dev_sx2 
update sensevoice small with timestamp
 2024-12-05 19:30:30 +08:00
shixian
026b8e3fdc update sensevoice small with timestamp 2024-12-05 19:29:19 +08:00
Shi Xian
0efc87352c
Merge pull request #2267 from modelscope/dev_sx2 
fix model_wrapper and seaco finetune
 2024-12-05 15:15:38 +08:00
shixian
e71546b06d debug 2024-12-05 15:14:47 +08:00
Thomas Young
46721dc84a
fix export error if using cpu device; fix model path (#2265) 
Co-authored-by: siyuan.yang <siyuan.yang@sophgo.com>
 2024-12-05 11:01:29 +08:00
will_wang
0c3c9be2c4
paraformer onnx fp16导出方案 (#2264) 
* onnx fp16模型

* paraformer-offline [fp32 fp16 onnx-gpu]

* paraformer-offline [fp32 fp16 onnx-gpu]

* Update export.py

---------

Co-authored-by: zhifu gao <zhifu.gzf@alibaba-inc.com>
 2024-12-04 17:47:31 +08:00
Tang Linjie
8b1be8c3cb
feat: speed up fbank's lfr (#2246) 
Co-authored-by: linjie.tang <linjie.tang@sophgo.com>
 2024-11-30 13:05:39 +08:00
莫拉古
ae49b2a8e1
变量名写错了 (#2249) 2024-11-29 09:55:43 +08:00
游雁
294e9e7d4b v1.1.16 2024-11-28 15:53:41 +08:00
游雁
4b3a28cbc5 pcm unfix 2024-11-28 15:53:17 +08:00
游雁
345900442d Merge branch 'main' of github.com:alibaba-damo-academy/FunASR 
merge
 2024-11-28 15:50:21 +08:00
游雁
62aaba1940 print 2024-11-28 15:48:37 +08:00
zhifu gao
bb6018e753
Update README.md 2024-11-22 16:27:09 +08:00
游雁
f4c6af4528 docs 2024-11-21 16:07:06 +08:00
pointerhacker
37d6930561
fix:添加音频码率验证以防止模型异常 (#2219) 
Co-authored-by: zhaochaojin <zhaochaojin@didiglobal.com>
 2024-11-20 18:39:05 +08:00
Yabin Li
141df861cb
Update websocket_protocol_zh.md 2024-11-20 15:22:59 +08:00