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
1,263 Commits 25 Branches 4 Tags 135 MiB
74a2059e9c
Commit Graph

204 Commits

Author SHA1 Message Date
游雁
cdeb0389f2 websocket 2023-03-23 19:44:59 +08:00
游雁
7a8bedace2 websocket 2023-03-23 17:12:02 +08:00
游雁
174053cfca vad 2023-03-22 13:46:52 +08:00
mengzhe.cmz
586c7024ef fix demo service 2023-03-22 11:21:39 +08:00
zhifu gao
1f0f44bd07
Merge pull request #276 from alibaba-damo-academy/dev_sx 
Dev sx
 2023-03-21 20:18:21 +08:00
游雁
752fd0b8a9 Merge branch 'main' of github.com:alibaba-damo-academy/FunASR 
add
 2023-03-21 20:05:26 +08:00
游雁
67db551bb0 vad 2023-03-21 20:05:12 +08:00
shixian.shi
1292a00b06 debug 2023-03-21 19:43:29 +08:00
shixian.shi
8cd93a1fc7 asr_inference pipeline supports combine tp model 2023-03-21 19:41:40 +08:00
dingbig
d80d046365 fixed token_int is zero bug and add more puncs to sentence 
1)If token_int is 0, the following process will crash. This BUG has been fixed. In fact, when token_int=0, there is no need to continue processing.
2)modify time_stamp_sentence to support more punc.
 2023-03-21 17:11:49 +08:00
shixian.shi
3258d2be0a debugging 2023-03-21 14:01:29 +08:00
speech_asr
aa1f23e0a7 update 2023-03-17 10:56:18 +08:00
zhifu gao
e62e208a5c
Merge pull request #251 from alibaba-damo-academy/dev_lhn 
Dev lhn
 2023-03-16 19:50:52 +08:00
Zhihao Du
38de2af5bf
Merge branch 'main' into dev_dzh 2023-03-16 19:41:34 +08:00
游雁
8f8484bfa3 vad 2023-03-16 19:37:48 +08:00
zhifu gao
d783b24ba7
Merge pull request #199 from alibaba-damo-academy/dev_xw 
[Quantization] post training quantization
 2023-03-16 19:34:52 +08:00
志浩
2868fe3df4 Merge branch 'main' into dev_dzh 2023-03-16 19:24:21 +08:00
志浩
49ded3a686 modify diar pipeline 2023-03-16 19:18:03 +08:00
speech_asr
2ba4683eb2 update 2023-03-16 11:14:42 +08:00
speech_asr
c3bce4c288 update 2023-03-16 10:44:15 +08:00
speech_asr
7ee716759b update 2023-03-15 17:22:01 +08:00
speech_asr
b4598f30a5 update 2023-03-15 17:20:24 +08:00
speech_asr
dd4946a50d update 2023-03-15 16:44:59 +08:00
speech_asr
7c6ed3830a update 2023-03-15 16:39:40 +08:00
speech_asr
429ea5d378 update 2023-03-15 15:48:35 +08:00
speech_asr
e9f6703350 update 2023-03-15 15:29:31 +08:00
speech_asr
2f933cb101 update 2023-03-15 15:23:08 +08:00
speech_asr
85c1848286 update 2023-03-15 15:17:27 +08:00
speech_asr
2cfe010d7b update 2023-03-15 14:42:32 +08:00
speech_asr
4d60eb6ada update 2023-03-15 11:12:51 +08:00
speech_asr
46d9cc0b37 update 2023-03-14 22:54:24 +08:00
游雁
4bdce2285b rtf 2023-03-14 19:46:14 +08:00
Lizerui9926
a7ab8bd688
Merge pull request #230 from alibaba-damo-academy/dev_wjm 
Dev wjm
 2023-03-14 16:45:30 +08:00
speech_asr
ad2ef72341 update ola 2023-03-14 11:33:20 +08:00
speech_asr
7de11ad9ef update ola 2023-03-14 10:36:20 +08:00
仁迷
3762d21300 add streaming paraformer code 2023-03-13 22:02:54 +08:00
hnluo
ea5ff2de19
Merge pull request #222 from alibaba-damo-academy/dev_zly 
fix the output of vad_results is null
 2023-03-13 20:15:50 +08:00
凌匀
85566dbb2a fix the output of vad_results is null 2023-03-13 20:00:19 +08:00
凌匀
c81e3096b2 fix the output of vad_results is null 2023-03-13 19:57:08 +08:00
hnluo
08d6f5cc1c
Merge pull request #221 from alibaba-damo-academy/dev_zly 
update vad_inference_online.py
 2023-03-13 19:18:14 +08:00
凌匀
2af58ee953 update vad_inference_online.py 2023-03-13 19:14:43 +08:00
zhifu gao
0a729038cf
Merge pull request #218 from alibaba-damo-academy/dev_ts 
update timestamp related codes and egs_modelscope
 2023-03-13 17:47:56 +08:00
shixian.shi
f5aa97f7bf update params name 2023-03-13 17:39:18 +08:00
shixian.shi
a1fe3c635f update tp inference 2023-03-13 17:26:20 +08:00
凌匀
6da711a8d3 support vad_inference_online 2023-03-13 16:45:00 +08:00
shixian.shi
0766a89c8d bug fix 2023-03-13 16:15:31 +08:00
shixian.shi
76fd90d230 add class TimestampPredictor in e2e 2023-03-13 16:09:41 +08:00
shixian.shi
5a7ee30783 update timestamp related codes and egs_modelscope 2023-03-13 15:21:13 +08:00
yufan
56d13e2370
Update asr_inference_mfcca.py 2023-03-11 17:25:38 +08:00
Xian Shi
24fbc7efcb
Merge pull request #203 from alibaba-damo-academy/dev_tp 
Dev tp
 2023-03-10 15:00:45 +08:00
shixian.shi
7ce644eefd timestamp pipeline (alone) 2023-03-10 14:41:24 +08:00
shixian.shi
ca98012cd2 update tp_inference 2023-03-10 10:50:28 +08:00
shixian.shi
ed2370591f update tp_inference 2023-03-10 10:29:34 +08:00
shixian.shi
3ff9f5bf77 update timestamp inference 2023-03-09 17:22:00 +08:00
shixian.shi
900346d13d update tp_inference outputs 2023-03-09 16:36:19 +08:00
shixian.shi
c441eb08c4 tp_inference device bug 2023-03-09 15:26:03 +08:00
仁迷
62c592fac1 support mfcca infenence 2023-03-09 14:51:56 +08:00
shixian.shi
3610b3f48a update frontend in pipeline 2023-03-09 13:19:09 +08:00
shixian.shi
1582bad4b5 update timestamp infer param name 2023-03-08 17:02:50 +08:00
shixian.shi
31cda51dfa update timestamp pipelien 2023-03-08 16:38:28 +08:00
shixian.shi
4fb44fb330 update timestamp pipeline 2023-03-08 16:29:33 +08:00
mengzhe.cmz
4de9fe6cf6 punc vad realtime infer 2023-03-07 18:25:47 +08:00
北念
af3fb57fa9 support BiCifParaformer timestamp output without vad 2023-03-03 10:35:03 +08:00
游雁
1b6f5d39f4 vad 2023-03-02 17:13:00 +08:00
九耳
ee06cb9c68 punctuation:add training code, support largedataset 2023-02-28 18:11:12 +08:00
凌匀
3388361d3b update vad inference 2023-02-28 14:33:40 +08:00
zhifu gao
8cc5bbf99a
Merge pull request #159 from alibaba-damo-academy/dev_dzh 
Dev dzh
 2023-02-27 17:01:48 +08:00
志浩
e14323e6ab unit test modelscope for sd 2023-02-27 16:33:31 +08:00
志浩
bc145655e4 fixbug sond initial 2023-02-27 15:17:48 +08:00
凌匀
31eed1834f in_cache & support soundfile read 2023-02-27 13:33:55 +08:00
志浩
3b42ace3d4 fixbug for sd and sv 2023-02-27 12:22:34 +08:00
志浩
267dddcdbb fixbug for sd and sv 2023-02-27 11:48:09 +08:00
北念
cfa9401d9d modify contextual hotword parameter 2023-02-24 11:03:20 +08:00
志浩
04a7ce3205 sond pipeline 2023-02-23 17:53:04 +08:00
仁迷
09ff7d4516 fix uniasr decoding bug 2023-02-23 16:28:05 +08:00
游雁
7bb2dfba0c bugfix 2023-02-23 11:49:39 +08:00
Xian Shi
906c61a6f4
Merge pull request #147 from dingbig/main 
Add sentence timestamp support
 2023-02-22 20:23:29 +08:00
dingbig
bea5d98423 Add sentence timestamp support 
Added support for statement event timestamp, which is particularly useful for applications such as lyrics and subtitles.
 2023-02-22 19:48:50 +08:00
北念
f13cfbc18e support hotword parameter passing in the pipeline forward 2023-02-21 17:34:45 +08:00
游雁
2c3f49cd21 readme 2023-02-20 16:08:23 +08:00
zhifu gao
0d15538835
Merge pull request #133 from alibaba-damo-academy/dev_lyb 
fix bug: output_dir
 2023-02-17 14:51:47 +08:00
wucong.lyb
637a32c7de fix bug: output_dir 2023-02-17 14:37:00 +08:00
lzr265946
267e2d09e6 support paraformer-large-contextual with vad and punc model 2023-02-17 11:12:03 +08:00
zhifu gao
6baf10d5d1
Merge branch 'main' into dev_zly 2023-02-17 10:31:05 +08:00
凌匀
8689fb676d support asr_inference_paraformer_vad_punc 2023-02-16 23:08:56 +08:00
凌匀
91027ddab4 fix vad results bug 2023-02-16 22:11:18 +08:00
游雁
b841635a53 amp pipeline 2023-02-16 20:04:21 +08:00
游雁
6023271be6 amp pipeline 2023-02-16 18:54:13 +08:00
凌匀
41b1d35048 update vad_inference.py 2023-02-16 17:02:56 +08:00
zhifu gao
6dcca251b3
Merge pull request #124 from alibaba-damo-academy/dev_lzr 
remove useless code
 2023-02-16 15:26:22 +08:00
lzr265946
546262a0c6 remove useless code 2023-02-16 15:22:14 +08:00
凌匀
d6fdd1c793 support vad streaming decoder 2023-02-16 14:56:32 +08:00
jiangyu.xzy
484d9aa560 remove global vars 2023-02-15 20:23:13 +08:00
仁迷
b22c0d2284 add decoding model parameters 2023-02-15 19:29:23 +08:00
游雁
560dafa8ad mfcca 2023-02-14 15:35:47 +08:00
yufan-aslp
a319bf6e5f dev_yufan egs_mfcca update 2023-02-14 14:54:04 +08:00
lzr265946
83bede2646 support hotword txt url input 2023-02-13 11:38:03 +08:00
志浩
f6a1cdaf34 add sond model 2023-02-10 18:56:14 +08:00
lzr265946
7aa2e885f4 support for turning off timestamps 2023-02-10 13:46:01 +08:00
wucong.lyb
9e8a52153d add language model infer pipeline 2023-02-10 10:54:27 +08:00