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
3,695 Commits 25 Branches 4 Tags 135 MiB
e4035edb46
Commit Graph

3695 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
speech_asr
b0b796f9a4 Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main 2023-12-15 14:04:07 +08:00
speech_asr
630509da0f update funasr_wss_client.py 2023-12-15 14:03:43 +08:00
bltcn
b32d5a2b7e
modify link (#1183) 
* commit web page vue
 2023-12-15 10:59:37 +08:00
zhifu gao
72c4568049
Update readme.md 2023-12-15 10:51:50 +08:00
雾聪
009f4fed79 update funasr-wss-client 2023-12-15 10:30:26 +08:00
雾聪
3313eb681e fi bug of FfmpegLoad 2023-12-15 10:27:59 +08:00
游雁
7012ca2efc funasr2 paraformer biciparaformer contextuaparaformer 2023-12-13 20:08:55 +08:00
游雁
806a03609d funasr2 paraformer biciparaformer contextuaparaformer 2023-12-13 19:43:13 +08:00
雾聪
51f7b76660 adapted pcm to 8k online 2023-12-13 17:30:38 +08:00
雾聪
de87e1d180 adapted pcm to 8k 2023-12-13 13:57:59 +08:00
Yabin Li
a0048dc766
8k (#1174) (#1175) 
* Adaptive 8K

* fix FfmpegLoad 8k

Co-authored-by: cdevelop <cdevelop@qq.com>
 2023-12-13 09:50:58 +08:00
雾聪
3c83d64c84 fst: support eng hotword 2023-12-12 11:11:02 +08:00
雾聪
d674c29323 add timestamp smooth 2023-12-11 15:51:38 +08:00
游雁
6745487e9c funasr2 2023-12-11 13:43:39 +08:00
游雁
d77910eb6d funasr2 2023-12-11 13:42:40 +08:00
zhifu gao
172e7ac986
Revert "Dev gzf funasr2" (#1164) 2023-12-11 10:17:22 +08:00
zhifu gao
85cabd30a9
update with main (#1163) 
* v0.8.7

* update cmd version

* set openfst HAVE_BIN/HAVE_SCRIPT off for win32

* 修复为支持新版本的热词 (#1137)

* update CMakeLists.txt

* Revert "update CMakeLists.txt"

This reverts commit 54bcd1f674.

* rm log.h for wins-websocket

* fix bug of websocket lock blocking

* update funasr-wss-server

* update model-revision by model name

* update funasr-wss-server-2pass

* 增加分角色语音识别对ERes2Net模型的支持。

* Update README.md (#1140)

minor fix

* automatically configure parameters such as decoder-thread-num

* update docs

* update docs

* update docs

* 分角色语音识别支持更多的模型

* update spk inference

* remove never use code (#1151)

* fix loss normalization for ddp training

* fix loss normalization for ddp training

* fix loss normalization for ddp training

---------

Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com>
Co-authored-by: 夜雨飘零 <yeyupiaoling@foxmail.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>
Co-authored-by: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
 2023-12-11 10:10:54 +08:00
zhifu gao
c0008fd461
Merge branch 'dev_gzf_funasr2' into main 2023-12-11 10:10:40 +08:00
hnluo
202ab8a2c9
Merge pull request #1161 from alibaba-damo-academy/dev_lhn 
fix loss normalization for ddp training
 2023-12-08 16:43:48 +08:00
haoneng.lhn
ace42e5043 fix loss normalization for ddp training 2023-12-08 16:39:38 +08:00
hnluo
aab1fcd6b6
Merge pull request #1160 from alibaba-damo-academy/dev_lhn 
fix loss normalization for ddp training
 2023-12-08 16:22:44 +08:00
haoneng.lhn
acb9a0fec8 fix loss normalization for ddp training 2023-12-08 16:19:00 +08:00
zhifu gao
5cf512419c
update with main (#1158) 
* v0.8.7

* update cmd version

* set openfst HAVE_BIN/HAVE_SCRIPT off for win32

* 修复为支持新版本的热词 (#1137)

* update CMakeLists.txt

* Revert "update CMakeLists.txt"

This reverts commit 54bcd1f674.

* rm log.h for wins-websocket

* fix bug of websocket lock blocking

* update funasr-wss-server

* update model-revision by model name

* update funasr-wss-server-2pass

* 增加分角色语音识别对ERes2Net模型的支持。

* Update README.md (#1140)

minor fix

* automatically configure parameters such as decoder-thread-num

* update docs

* update docs

* update docs

* 分角色语音识别支持更多的模型

* update spk inference

* remove never use code (#1151)

* fix loss normalization for ddp training

---------

Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com>
Co-authored-by: 夜雨飘零 <yeyupiaoling@foxmail.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>
Co-authored-by: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
 2023-12-07 16:57:03 +08:00
hnluo
73959c6e8e
Merge pull request #1157 from alibaba-damo-academy/dev_lhn 
fix loss normalization for ddp training
 2023-12-07 14:54:25 +08:00
haoneng.lhn
4152cf4615 fix loss normalization for ddp training 2023-12-07 14:49:34 +08:00
游雁
fc246ab820 funasr2 2023-12-07 00:27:00 +08:00
游雁
99340740f5 funasr2 2023-12-07 00:23:25 +08:00
游雁
15868f6230 funasr2 2023-12-06 23:50:54 +08:00
游雁
d6aa93946e funasr2 2023-12-06 19:55:24 +08:00
zhifu gao
81acb17544
update with main (#1152) 
* v0.8.7

* update cmd version

* set openfst HAVE_BIN/HAVE_SCRIPT off for win32

* 修复为支持新版本的热词 (#1137)

* update CMakeLists.txt

* Revert "update CMakeLists.txt"

This reverts commit 54bcd1f674.

* rm log.h for wins-websocket

* fix bug of websocket lock blocking

* update funasr-wss-server

* update model-revision by model name

* update funasr-wss-server-2pass

* 增加分角色语音识别对ERes2Net模型的支持。

* Update README.md (#1140)

minor fix

* automatically configure parameters such as decoder-thread-num

* update docs

* update docs

* update docs

* 分角色语音识别支持更多的模型

* update spk inference

* remove never use code (#1151)

---------

Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com>
Co-authored-by: 夜雨飘零 <yeyupiaoling@foxmail.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>
 2023-12-06 19:54:37 +08:00
游雁
1c2eb051cd funasr2 2023-12-06 19:45:49 +08:00
游雁
e98e10639d funasr2 2023-12-06 19:42:02 +08:00
夜雨飘零
6f88a689af
remove never use code (#1151) 2023-12-06 17:02:51 +08:00
游雁
27f31cd42b funasr2 2023-12-06 17:01:12 +08:00
shixian.shi
e54535e5eb update spk inference 2023-12-06 11:29:43 +08:00
Shi Xian
b3fcd42bf6
Merge pull request #1144 from yeyupiaoling/main 
增加【Paraformer分角色语音识别-中文-通用】对ERes2Net模型的支持
 2023-12-06 11:14:57 +08:00
夜雨飘零
18b1449d1f 分角色语音识别支持更多的模型 2023-12-05 22:04:14 +08:00
雾聪
089172899b update docs 2023-12-05 14:58:29 +08:00
雾聪
2f5b2c5778 update docs 2023-12-05 14:47:49 +08:00
雾聪
4e7b67d756 update docs 2023-12-05 14:43:36 +08:00
雾聪
b6190f04ff automatically configure parameters such as decoder-thread-num 2023-12-05 14:22:10 +08:00
Ikko Eltociear Ashimine
a8e364d08c
Update README.md (#1140) 
minor fix
 2023-12-04 23:14:07 +08:00
夜雨飘零
73613cefc9 增加分角色语音识别对ERes2Net模型的支持。 2023-12-04 21:41:07 +08:00
雾聪
d4b6770d03 update funasr-wss-server-2pass 2023-12-04 11:18:04 +08:00
雾聪
ef07c0d48f update model-revision by model name 2023-12-04 11:15:05 +08:00
雾聪
6626b89013 update funasr-wss-server 2023-12-01 10:03:41 +08:00
雾聪
467186eec4 fix bug of websocket lock blocking 2023-11-30 19:08:38 +08:00
雾聪
9fa2b2128d rm log.h for wins-websocket 2023-11-30 11:15:47 +08:00
雾聪
d7f4fe61ff Revert "update CMakeLists.txt" 
This reverts commit 54bcd1f674.
 2023-11-30 10:43:52 +08:00
雾聪
168d4ac2ff Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main 2023-11-30 09:49:40 +08:00