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
4,172 Commits 25 Branches 4 Tags 136 MiB
ae04f1e6c0
Commit Graph

502 Commits

Author SHA1 Message Date
haoneng.lhn
dcb92f13ed add paraformer online opt infer code 2023-09-14 16:46:30 +08:00
aky15
5c9bdfa238
Merge pull request #952 from alibaba-damo-academy/aky15-patch-1 
Update asr_infer.py
 2023-09-14 16:12:53 +08:00
aky15
bbdb9bf1f5
Update asr_inference_launch.py 
rename simu_streaming to fake_streaming
 2023-09-14 16:10:54 +08:00
aky15
11d5964951
Update asr_infer.py 
rename simu_streaming to fake_streaming
 2023-09-14 16:08:53 +08:00
haoneng.lhn
f41a1276ff add paraformer online opt infer code 2023-09-14 12:25:44 +08:00
haoneng.lhn
5f088a67cd add paraformer online opt infer code 2023-09-13 20:02:54 +08:00
shixian.shi
33a9bafbcc fix bug in timestamp inference 2023-09-13 16:54:05 +08:00
shixian.shi
eb9989745e bug fix in timestamp inference 2023-09-13 16:52:54 +08:00
hnluo
b091828cea
Merge pull request #936 from alibaba-damo-academy/dev_lhn 
Dev lhn
 2023-09-13 10:54:55 +08:00
chenmengzheAAA
60d78d9d84
Merge pull request #941 from alibaba-damo-academy/dev_cmz 
change eng punc in offline model
 2023-09-12 22:22:06 +08:00
Xian Shi
57ccdf04e0
Merge pull request #939 from alibaba-damo-academy/dev_sxfix 
Bug fix
 2023-09-12 19:56:29 +08:00
mengzhe.cmz
1f214b2bba change eng punc in offline model 2023-09-12 17:56:36 +08:00
haoneng.lhn
2165d5de05 fix decoding_ind none bug 2023-09-12 13:00:16 +08:00
haoneng.lhn
eed5cbb945 fix decoding_ind none bug 2023-09-12 12:55:19 +08:00
haoneng.lhn
39ae137532 fix decoding_ind params conflict bug 2023-09-11 18:47:00 +08:00
haoneng.lhn
e60ac4bc99 support chunk size select for chunk-hopping encoder 2023-09-11 17:36:27 +08:00
lzr265946
9b4e0969f2 fix transformerLM inference recipe 2023-09-07 17:19:02 +08:00
hnluo
602d3b5e2e
fix vad max_end_sil bug 2023-09-06 19:13:43 +08:00
shixian.shi
13c2af5de4 fix empty timestamp list inference 2023-09-06 11:51:46 +08:00
aky15
e708b87a40 rnnt infer bug fix 2023-08-14 15:15:50 +08:00
aky15
a5cd4bb473 support offline inference for unified streaming/non-streaming rnnt 2023-08-14 10:54:23 +08:00
haoneng.lhn
b1e980d501 add mossformer code 2023-08-10 14:40:07 +08:00
hnluo
bce7248763 add mossformer code 2023-08-10 12:38:55 +08:00
jmwang66
651737380b
Merge branch 'main' into dev_wjm_modelscope 2023-08-09 16:48:02 +08:00
志浩
e361e7d59f TOLD/SOND: rename diar_smooth_size to smooth_size 2023-08-01 17:50:46 +08:00
志浩
4bc6db3ef8 TOLD: add TOLD/SOND recipe on callhome 2023-08-01 17:03:39 +08:00
嘉渊
7ea3836893 update 2023-08-01 14:18:32 +08:00
hnluo
c64d4b25e2
Merge pull request #787 from alibaba-damo-academy/dev_lhn 
Update asr_inference_launch.py
 2023-07-28 17:43:47 +08:00
hnluo
0f18a6d2a0
Update asr_inference_launch.py 2023-07-28 17:42:21 +08:00
嘉渊
96ae31d5b6 update 2023-07-27 15:37:02 +08:00
嘉渊
d5c818131b update 2023-07-27 15:24:14 +08:00
嘉渊
f16c6c2926 update 2023-07-26 19:32:30 +08:00
嘉渊
8e53dd6b77 update 2023-07-26 19:11:19 +08:00
嘉渊
fcac51fbd7 update 2023-07-26 17:41:14 +08:00
hnluo
0063e4356a
Merge pull request #768 from alibaba-damo-academy/dev_lhn 
Dev lhn
 2023-07-21 15:07:34 +08:00
游雁
b06c980504 bugfix long wav batch_size_token_threshold_ms 2023-07-21 10:30:38 +08:00
游雁
5d315365e0 bugfix long wav batch_size_token_threshold_ms 2023-07-21 10:26:34 +08:00
游雁
4bc5b3694c bugfix long wav 2023-07-21 09:21:24 +08:00
游雁
3685afda47 bugfix long wav 2023-07-20 20:40:02 +08:00
haoneng.lhn
3e8159e5b0 add lora finetune code 2023-07-20 18:43:38 +08:00
haoneng.lhn
36c43d4c9f add lora finetune code 2023-07-20 18:33:54 +08:00
aky15
b5ed957ae9
Dev bat modelscope2 (#757) 
* remove from_pretrained

* bug fix for bat infer

---------

Co-authored-by: aky15 <ankeyu.aky@11.17.44.249>
 2023-07-20 16:32:36 +08:00
aky15
97c617854e
remove from_pretrained (#754) 
Co-authored-by: aky15 <ankeyu.aky@11.17.44.249>
 2023-07-20 15:35:39 +08:00
haoneng.lhn
b8e2cab7ee add lora finetune code 2023-07-20 09:46:33 +08:00
haoneng.lhn
7a19c52602 add lora finetune code 2023-07-19 16:41:39 +08:00
shixian.shi
2f5d11f8e2 bug fix for empty audio 2023-07-19 11:20:24 +08:00
mengzhe.cmz
b6b63936c7 add punc large model modelscope runtime; fix train bug 2023-07-18 17:32:38 +08:00
haoneng.lhn
16c4154245 add lora finetune code 2023-07-18 16:47:27 +08:00
游雁
579afd6ac8 docs and GPU memory release 2023-07-14 19:03:15 +08:00
嘉渊
d6fc85135b update 2023-07-13 15:33:30 +08:00
aky15
c5274e728a
Update asr_inference_launch.py (#719) 
update bat infer for modelscope
 2023-07-10 12:48:50 +08:00
游雁
7a207808bc np fix bug 2023-07-06 19:13:00 +08:00
shixian.shi
b7befd113a bug fix 2023-07-05 16:04:51 +08:00
jmwang66
92dec9b331
Merge pull request #703 from alibaba-damo-academy/dev_wjm 
fix load bug
 2023-07-04 20:01:14 +08:00
Xian Shi
11daec8222
bug fix for asr_launch empty speech (#709) 2023-07-04 19:57:17 +08:00
Xian Shi
c20c871e9f
Merge pull request #673 from alibaba-damo-academy/dev_clas 
contextual paraformer related update: infer and finetune
 2023-07-04 19:57:04 +08:00
嘉渊
ba3d455b21 update 2023-07-03 21:51:17 +08:00
aky15
05ada32da8
boundary aware transducer (#691) 
* boundary aware transducer

* resolve conflict

* delete type check

---------

Co-authored-by: aky15 <ankeyu.aky@11.17.44.249>
 2023-07-02 09:14:17 +08:00
jmwang66
98abc0e5ac
update setup (#686) 
* update

* update setup

* update setup

* update setup

* update setup

* update setup

* update setup

* update

* update

* update setup
 2023-06-29 16:30:39 +08:00
shixian.shi
007a8dc289 update 2023-06-27 19:59:47 +08:00
shixian.shi
8d519b9dc6 update 2023-06-27 19:48:51 +08:00
shixian.shi
92e14eb734 debug 2023-06-27 17:24:19 +08:00
haoneng.lhn
a0defaf40e fix loading multi-channel mp3 file bug 2023-06-27 13:12:42 +08:00
haoneng.lhn
e677eb4b13 fix torchaudio load mp3 bug 2023-06-26 17:13:22 +08:00
hnluo
e83292715f
fix english hotwords bug 2023-06-26 11:51:19 +08:00
haoneng.lhn
6a3d31dc55 fix english hotwards bug 2023-06-21 17:40:29 +08:00
jmwang66
4e0fcee2a9
Merge branch 'main' into dev_wjm_infer 2023-06-19 20:28:23 +08:00
游雁
6001cffa9c paraformer long cpu 2023-06-19 19:13:36 +08:00
嘉渊
a17c5cc3e7 update repo 2023-06-17 13:30:32 +08:00
yhliang
e8528b8f62
Dev lyh (#645) 
* update

* update

* fix bug

* fix bug
 2023-06-16 20:16:47 +08:00
嘉渊
0b45320b57 update repo 2023-06-15 21:35:30 +08:00
嘉渊
eee72548d7 update repo 2023-06-15 17:25:46 +08:00
嘉渊
04528cb292 update repo 2023-06-15 17:20:07 +08:00
嘉渊
27fddb4982 update repo 2023-06-15 16:41:37 +08:00
嘉渊
ca666ab7d8 update repo 2023-06-15 16:18:21 +08:00
嘉渊
ca6b2e29fd update repo 2023-06-15 15:56:19 +08:00
嘉渊
0c4fbea66b update repo 2023-06-15 15:39:22 +08:00
嘉渊
4b30f336ee update repo 2023-06-15 15:03:21 +08:00
嘉渊
3c631a9c12 update repo 2023-06-14 20:49:47 +08:00
嘉渊
0f3a4ca84d update repo 2023-06-14 17:29:57 +08:00
嘉渊
7d6177b43f update repo 2023-06-14 16:00:53 +08:00
嘉渊
3d70934e7f update repo 2023-06-14 15:09:56 +08:00
嘉渊
94436935bd update repo 2023-06-14 15:08:20 +08:00
嘉渊
fee48e7a62 update repo 2023-06-14 15:02:38 +08:00
嘉渊
0b07e6af04 update repo 2023-06-14 14:56:31 +08:00
aky15
68ae83684f
Update asr_infer.py (#622) 
bug fix
 2023-06-12 21:41:41 +08:00
hnluo
4ce2e2d76c
Merge pull request #571 from alibaba-damo-academy/dev_lhn 
Dev lhn
 2023-05-31 18:42:38 +08:00
haoneng.lhn
a8381b2b57 add paraformer online infer and finetune recipe 2023-05-31 17:00:58 +08:00
haoneng.lhn
28cabff45f update 2023-05-31 15:42:43 +08:00
凌匀
7109589f0e support in_cache 2023-05-31 13:12:15 +08:00
haoneng.lhn
7ecf141574 update 2023-05-30 19:33:32 +08:00
haoneng.lhn
84b4a01979 add paraformer online infer and finetune 2023-05-26 11:43:27 +08:00
Zhihao Du
6cc2e585b7
fix oov bug for sond inference (#555) 2023-05-25 15:49:44 +08:00
hnluo
e0a8c4b006
Merge pull request #552 from alibaba-damo-academy/dev_wjm2 
update ASR recipe
 2023-05-25 11:08:46 +08:00
嘉渊
a5b1f9911c update repo 2023-05-24 11:52:19 +08:00
yhliang
72b2f1a023
update m2met2 (#543) 
* update m2met2

* update doc
 2023-05-24 10:52:57 +08:00
aky15
584d0bc0eb
Merge pull request #538 from alibaba-damo-academy/dev_aky2 
rnnt support wav input
 2023-05-23 17:49:01 +08:00
aky15
71f1059af9 rnnt support wav input 2023-05-23 10:48:56 +08:00
wucong.lyb
1ee853bff5 Merge branch 'main' of https://github.com/alibaba/FunASR into main 2023-05-22 19:12:17 +08:00
wucong.lyb
42e1259075 fix lm_inference_launch.py 2023-05-22 19:09:30 +08:00
游雁
3cde6fe8e0 bugfix paraformer large long 2023-05-22 16:25:48 +08:00
haoneng.lhn
a2a70f776a add paraforme infer code 2023-05-22 15:39:09 +08:00
游雁
5eb52f9c73 bugfix 2023-05-22 13:08:31 +08:00
haoneng.lhn
27f6d173ec update paraformer online text postprocess 2023-05-19 13:23:11 +08:00
haoneng.lhn
dcc4f728cd update paraformer online text postprocess 2023-05-19 13:19:55 +08:00
haoneng.lhn
025df72c10 update 2023-05-18 21:10:16 +08:00
haoneng.lhn
47bd60924c fix paraformer online fbank cache bug 2023-05-18 19:52:10 +08:00
lingyunfly
06639d8e91
Update vad_inference_launch.py 2023-05-18 14:16:26 +08:00
lingyunfly
19f4fae784
Update vad_inference_launch.py 2023-05-18 14:15:27 +08:00
嘉渊
17eaf419c0 Merge branch 'dev_infer' of https://github.com/alibaba/FunASR into dev_infer 2023-05-18 14:10:11 +08:00
嘉渊
bb8ddea4cb update repo 2023-05-18 14:09:58 +08:00
aky15
6c381c2700 modify rnnt infer 2023-05-18 11:44:48 +08:00
aky15
429995f4d0 Merge branch 'dev_infer' of https://github.com/alibaba-damo-academy/FunASR into dev_infer 2023-05-17 17:38:49 +08:00
aky15
9d01231fa6 rnnt继承ASRTask 2023-05-17 17:34:21 +08:00
haoneng.lhn
a7814a7bc3 fix paraformer online last chunk decoding strategy 2023-05-17 17:13:32 +08:00
嘉渊
e1ba6bc138 Merge branch 'dev_infer' of https://github.com/alibaba/FunASR into dev_infer 2023-05-17 15:16:06 +08:00
嘉渊
d1374e9c80 update repo 2023-05-17 15:15:51 +08:00
志浩
3be66ec19a confirm inference and demo files for SV and SD tasks 2023-05-17 15:04:53 +08:00
游雁
3d9f094e96 train 2023-05-16 23:48:00 +08:00
游雁
d5d7363da1 train 2023-05-16 22:56:20 +08:00
游雁
b8e34a1342 inference 2023-05-16 20:12:44 +08:00
游雁
f01980d169 inference 2023-05-16 19:34:45 +08:00
游雁
0271fbe4fd inference 2023-05-16 18:53:33 +08:00
嘉渊
94a4dbba3d Merge branch 'dev_infer' of https://github.com/alibaba/FunASR into dev_infer 2023-05-16 18:37:49 +08:00
嘉渊
878e6db248 update repo 2023-05-16 18:37:34 +08:00
北念
9516125a7c update asr_inference_launch for hotword input 2023-05-16 17:34:36 +08:00
嘉渊
8629d30d3d update repo 2023-05-16 15:06:25 +08:00
游雁
4cd79db451 inference 2023-05-16 14:08:57 +08:00
游雁
d105ce0d6b inference 2023-05-16 13:58:11 +08:00
游雁
0f3571db84 inference 2023-05-16 09:40:10 +08:00
嘉渊
688fb902dd update repo 2023-05-15 10:59:59 +08:00
游雁
4ac582341c inference 2023-05-15 00:32:33 +08:00
嘉渊
ebdf631d98 update repo 2023-05-12 11:22:58 +08:00
嘉渊
687fe6dbab update repo 2023-05-12 10:10:12 +08:00
游雁
475064f914 paraformer vad punc 2023-05-11 19:35:10 +08:00
游雁
9d6aad2a44 paraformer vad punc 2023-05-11 19:06:18 +08:00
shixian.shi
8c732716d6 update timestamp for batch inference 2023-05-11 16:55:50 +08:00
shixian.shi
c165a9dd22 update 2023-05-11 16:13:50 +08:00
shixian.shi
b3bc53e332 update timestamp for batch inference 2023-05-11 15:50:17 +08:00
嘉渊
decdbc3c97 update repo 2023-05-11 15:13:25 +08:00
游雁
2b458b1a71 paraformer long batch infer sort 2023-05-10 21:59:41 +08:00
游雁
a97daeb247 paraformer long batch infer 2023-05-10 19:08:54 +08:00
zhifu gao
15d5ba7882
Merge pull request #479 from alibaba-damo-academy/dev_aky 
rnnt bug fix
 2023-05-09 13:56:58 +08:00
aky15
77045e7bb7 rnnt bug fix 2023-05-09 11:16:07 +08:00
jmwang66
8dab6d184a
Merge pull request #473 from alibaba-damo-academy/dev_smohan 
Add speaker-attributed ASR task for alimeeting (baseline for m2met2.0).
 2023-05-09 10:58:33 +08:00
游雁
c197b3aa85 fix vad cpu infer.sh batch=1 2023-05-08 22:06:44 +08:00
游雁
59f920f17c websocket python offline/online 2pass demo 2023-05-08 16:14:25 +08:00
smohan-speech
af6740a220 add speaker-attributed ASR task for alimeeting 2023-05-08 16:13:23 +08:00
mengzhe.cmz
3d7c0c5d2d fix vad realtime space bug 2023-05-08 12:44:50 +08:00
hnluo
30e4f1fa71
Merge pull request #469 from alibaba-damo-academy/dev_lhn 
update streaming paraformer text process
 2023-05-08 10:31:22 +08:00