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
4,841 Commits 25 Branches 4 Tags 136 MiB
58b52b344e
Commit Graph

529 Commits

Author SHA1 Message Date
zhifu gao
35b1c051f6
Dev gzf llm (#1493) 
* update

* update

* update

* update onnx

* update with main (#1492)

* contextual&seaco ONNX export (#1481)

* contextual&seaco ONNX export

* update ContextualEmbedderExport2

* update ContextualEmbedderExport2

* update code

* onnx (#1482)

* qwenaudio qwenaudiochat

* qwenaudio qwenaudiochat

* whisper

* whisper

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* export onnx

* export onnx

* export onnx

* dingding

* dingding

* llm

* doc

* onnx

* onnx

* onnx

* onnx

* onnx

* onnx

* v1.0.15

* qwenaudio

* qwenaudio

* issue doc

* update

* update

* bugfix

* onnx

* update export calling

* update codes

* remove useless code

* update code

---------

Co-authored-by: zhifu gao <zhifu.gzf@alibaba-inc.com>

* acknowledge

---------

Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>

* update onnx

* update onnx

---------

Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
 2024-03-14 09:33:30 +08:00
zhifu gao
a7d7a0f3a2
Dev gzf (#1467) 
* qwenaudio qwenaudiochat

* qwenaudio qwenaudiochat

* whisper

* whisper

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* export onnx

* export onnx

* export onnx

* dingding

* dingding

* llm

* doc

* onnx
 2024-03-11 19:24:44 +08:00
zhifu gao
4a7a984a5f
Dev gzf (#1465) 
* qwenaudio qwenaudiochat

* qwenaudio qwenaudiochat

* whisper

* whisper

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* export onnx

* export onnx

* export onnx

* dingding

* dingding

* llm
 2024-03-11 17:56:30 +08:00
zhifu gao
9d48230c4f
export onnx (#1457) 
* qwenaudio qwenaudiochat

* qwenaudio qwenaudiochat

* whisper

* whisper

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* export onnx

* export onnx
 2024-03-11 10:48:50 +08:00
zhifu gao
f2d8ded57f
export onnx (#1455) 
* qwenaudio qwenaudiochat

* qwenaudio qwenaudiochat

* whisper

* whisper

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* llm

* export onnx
 2024-03-11 01:24:43 +08:00
zhifu gao
790bf54944
Dev gzf (#1422) 
* fixbug

* qwenaudio

* qwenaudio whisper-openai v1.0.12
 2024-03-04 20:35:06 +08:00
zhifu gao
b9cfd9953a
Dev gzf (#1402) 
* init param
 2024-02-28 20:44:21 +08:00
游雁
7a4816651f init param 2024-02-28 14:38:05 +08:00
游雁
fa6f60fa76 update 2024-02-23 14:01:44 +08:00
游雁
8827e26b8d fp16 2024-02-23 00:58:18 +08:00
游雁
0587592632 train finetune demo 2024-02-22 11:20:04 +08:00
游雁
58b6154a73 update 2024-02-20 17:02:44 +08:00
游雁
ff4306346e aishell example 2024-02-19 21:26:25 +08:00
游雁
1448e021ac aishell example 2024-02-19 14:59:26 +08:00
zhifu gao
2ddfc27d5b
Funasr1.0 (#1343) 
* funasr1.0.5

* funasr1.0.5 audio samples input

* batch_type token

* batch_type token
 2024-02-01 17:29:28 +08:00
zhifu gao
2cca8104d2
Funasr1.0 (#1275) 
* funasr1.0 funetine

* funasr1.0 pbar

* update with main (#1260)

* Update websocket_protocol_zh.md

* update

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>

* update with main (#1264)

* Funasr1.0 (#1261)

* funasr1.0 funetine

* funasr1.0 pbar

* update with main (#1260)

* Update websocket_protocol_zh.md

* update

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>

* bug fix

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>

* funasr1.0 sanm scama

* funasr1.0 infer_after_finetune

* funasr1.0 fsmn-vad bug fix

* funasr1.0 fsmn-vad bug fix

* funasr1.0 fsmn-vad bug fix

* funasr1.0 finetune

* funasr1.0 finetune

* funasr1.0 finetune

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>
 2024-01-19 17:05:08 +08:00
zhifu gao
9a9c3b75b5
Funasr1.0 (#1261) 
* funasr1.0 funetine

* funasr1.0 pbar

* update with main (#1260)

* Update websocket_protocol_zh.md

* update

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com>
 2024-01-17 18:28:28 +08:00
游雁
2ed3f46f40 funasr1.0 finetune 2024-01-16 18:42:37 +08:00
游雁
bb97d3ed19 fix win bug 2024-01-16 15:47:01 +08:00
shixian.shi
b7cb19b01a update demo, readme 2024-01-16 11:30:25 +08:00
游雁
ce92fde1b7 funasr1.0 auto/ auto_model auto_frontend auto_tokenizer 2024-01-16 10:41:16 +08:00
shixian.shi
1233c0d3ff code update 2024-01-15 20:34:47 +08:00
shixian.shi
3fcb5dcfed update scripts 2024-01-15 20:25:35 +08:00
shixian.shi
97d648c255 code optimize, model update, scripts 2024-01-15 15:41:25 +08:00
游雁
2a0b2c795b funasr1.0 2024-01-15 11:51:26 +08:00
shixian.shi
0c75e62c6e update device bug 2024-01-12 18:10:18 +08:00
shixian.shi
09a28d19df update 2024-01-12 18:02:10 +08:00
shixian.shi
bcb8b0c3cb update (debugging) 2024-01-12 17:59:15 +08:00
游雁
0143122a4e funasr1.0 streaming demo 2024-01-12 10:27:36 +08:00
游雁
247c763286 funasr1.0 fsmn-vad streaming 2024-01-12 09:52:25 +08:00
shixian.shi
d72a4497a5 support oracle num for asr with spk 2024-01-11 19:16:51 +08:00
shixian.shi
7037971392 update asr with speaker 2024-01-11 17:03:00 +08:00
shixian.shi
668b830cb2 update cam++ for embed extract 2024-01-10 19:10:26 +08:00
游雁
1028a8a036 funasr1.0 paraformer_streaming WavFrontendOnline 2024-01-10 17:42:53 +08:00
游雁
d8b586e02c funasr1.0 modelscope 2024-01-09 20:33:12 +08:00
游雁
fb176404cf funasr1.0 emotion2vec 2024-01-08 16:20:45 +08:00
游雁
4f98546f36 load_audio_text_image_video 2024-01-05 16:55:07 +08:00
游雁
e63169bb06 prepare_data_iterator 2024-01-05 16:46:42 +08:00
游雁
32905d8cde funasr1.0 2024-01-05 11:52:48 +08:00
游雁
ccb9488954 funasr1.0 2023-12-27 23:03:49 +08:00
游雁
c6d6c932a0 funasr1.0 2023-12-27 16:43:30 +08:00
游雁
f6b611de44 funasr1.0 2023-12-27 15:52:16 +08:00
游雁
5a8f379084 vad + asr 2023-12-21 21:08:46 +08:00
游雁
a1b0cd33d5 rename register tables 2023-12-21 14:20:21 +08:00
游雁
c8bae0ec85 funasr2 2023-12-21 13:29:37 +08:00
游雁
00ea1186f9 funasr2 2023-12-19 22:53:18 +08:00
游雁
0e622e694e funasr2 2023-12-19 21:58:14 +08:00
游雁
298ddd13fb funasr2 2023-12-15 23:46:41 +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
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
27f31cd42b funasr2 2023-12-06 17:01:12 +08:00
shixian.shi
72fecc8e03 update asr_spk inference for shot utt 2023-11-24 14:29:33 +08:00
zhifu gao
7dadb793e6
Dev gzf funasr2 (#1111) 
* update funasr.text -> funasr.tokenizer fix bug export
 2023-11-23 16:04:37 +08:00
zhifu gao
b57b98364f
funasr v2 setup (#1106) 
* funasr v2 setup
 2023-11-22 00:36:35 +08:00
游雁
244c033fba python cli 2023-11-17 15:19:53 +08:00
北念
d90de51e76 fix paraformer finetune bug 2023-11-09 11:06:07 +08:00
Yabin Li
702ec03ad8
Dev new (#1065) 
* add hotword for deploy_tools

* Support wfst decoder and contextual biasing (#1039)

* Support wfst decoder and contextual biasing

* Turn on fstbin compilation

---------

Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com>

* mv funasr/runtime runtime

* Fix crash caused by OOV in hotwords list

* funasr infer

* funasr infer

* funasr infer

* funasr infer

* funasr infer

* fix some bugs about fst hotword; support wfst for websocket server and clients; mv runtime out of funasr; modify relative docs

* del onnxruntime/include/gflags

* update tensor.h

* update run_server.sh

* update deploy tools

* update deploy tools

* update websocket-server

* update funasr-wss-server

* Remove self loop propagation

* Update websocket_protocol_zh.md

* Update websocket_protocol_zh.md

* update hotword protocol

* author zhaomingwork: change hotwords for h5 and java

* update hotword protocol

* catch exception for json_fst_hws

* update hotword on message

* update onnx benchmark for ngram&hotword

* update docs

* update funasr-wss-serve

* add NONE for LM_DIR

* update docs

* update run_server.sh

* add whats-new

* modify whats-new

* update whats-new

* update whats-new

* Support decoder option for beam searching

* update benchmark_onnx_cpp

* Support decoder option for websocket

* fix bug of CompileHotwordEmbedding

* update html client

* update docs

---------

Co-authored-by: gongbo.gb <35997837+aibulamusi@users.noreply.github.com>
Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com>
Co-authored-by: 游雁 <zhifu.gzf@alibaba-inc.com>
 2023-11-07 18:34:29 +08:00
haoneng.lhn
e62eaed724 support resample for vad inference pipeline 2023-11-06 17:12:01 +08:00
Lizerui9926
8c904ecadd
Merge pull request #1053 from alibaba-damo-academy/dev_lzr_en 
support paraformer-16k-en finetune
 2023-11-02 17:13:18 +08:00
aky15
4e0404e04e fix rwkv infer bugs 2023-11-01 16:47:13 +08:00
北念
63b980b030 add bpemodel in build_trainer 2023-10-30 16:15:03 +08:00
shixian.shi
734a8caf55 update asr-spk inference 2023-10-24 17:06:41 +08:00
北念
a9600a123e fix import module dependency 2023-10-19 13:11:28 +08:00
北念
d53b970aec fix import module dependency 2023-10-19 10:43:04 +08:00
北念
72a0600129 fix bug in whisper inference 2023-10-17 14:15:14 +08:00
北念
fde48a8652 update egs_modelscope paraformer-large-en 2023-10-17 14:06:47 +08:00
北念
7c9b310e79 add whisper model inference pipeline 2023-10-12 14:31:39 +08:00
shixian.shi
78c78c39a9 big fix for speaker pipeline 2023-10-10 17:11:15 +08:00
Lizerui9926
35caed5dbc
Merge pull request #996 from alibaba-damo-academy/dev_lzr_en 
update asr postprocess_utils
 2023-10-10 16:00:50 +08:00
北念
a4de8b2a0a update asr postprocess_utils 2023-10-10 15:49:04 +08:00
shixian.shi
ac6afabdd1 update paraformer-speaker pipeline 2023-10-10 15:06:09 +08:00
shixian.shi
8a0930d682 paraformer-speaker inference pipeline 2023-10-10 11:35:42 +08:00
hnluo
8516d3e850
Merge pull request #970 from alibaba-damo-academy/dev_lhn 
Dev lhn
 2023-09-19 19:06:49 +08:00
游雁
895d84f24d v0.7.8 2023-09-18 10:49:27 +08:00
游雁
2bd8241948 Merge branch 'main' of github.com:alibaba-damo-academy/FunASR 
add
 2023-09-18 10:44:25 +08:00
游雁
74aa12ee4b docs 2023-09-18 10:43:27 +08:00
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