Commit Graph

4915 Commits

Author SHA1 Message Date
游雁
2ab9f44113 update 2024-07-04 09:48:20 +08:00
游雁
e8fe5711a2 update 2024-07-04 09:43:29 +08:00
游雁
1bf66d044f update 2024-07-03 17:53:23 +08:00
游雁
f9bb49c7ff update 2024-07-03 11:08:53 +08:00
游雁
c99ecd3687 update 2024-07-02 23:25:28 +08:00
游雁
1cf30eca36 update 2024-07-02 17:56:37 +08:00
游雁
2095a607e4 update 2024-07-02 17:41:09 +08:00
游雁
38f588479d update 2024-07-02 16:04:34 +08:00
游雁
df832b2b00 Merge branch 'dev_gzf_deepspeed' of github.com:alibaba-damo-academy/FunASR into dev_gzf_deepspeed
merge
2024-07-02 15:30:48 +08:00
游雁
8bde4a2cfb update 2024-07-02 15:30:32 +08:00
志浩
8839f1038c add TransformerEncoder_s0 2024-07-02 15:26:36 +08:00
志浩
988db3a2ed add TransformerEncoder_s0 2024-07-02 15:24:58 +08:00
游雁
99c732badb update 2024-07-02 15:04:39 +08:00
游雁
c37cf737b5 update 2024-07-02 14:48:42 +08:00
dcaaaa
7342c59449 add speech_qwen2 streaming fastapi 2024-07-02 14:14:17 +08:00
游雁
9d8a55c66a update 2024-07-02 14:11:50 +08:00
游雁
4784baf2af update 2024-07-02 14:10:57 +08:00
dcaaaa
f1874173c7 Merge branch 'dev_gzf_deepspeed' of http://gitlab.alibaba-inc.com/zhifu.gzf/FunASR into dev_gzf_deepspeed
merge online with local
2024-07-02 14:09:29 +08:00
dcaaaa
3d86f8626f add streaming decode fastapi 2024-07-02 14:08:59 +08:00
zhifu gao
b6aad84db6
Dev dzh deepspeed (#1867)
* add audio generator

* update ar model

---------

Co-authored-by: 志浩 <neo.dzh@alibaba-inc.com>
2024-07-02 13:52:03 +08:00
游雁
35d04ba357 update 2024-07-02 11:37:22 +08:00
游雁
97b86ed2b1 update 2024-07-02 10:51:43 +08:00
游雁
8e5294b9d3 update 2024-07-01 17:42:15 +08:00
游雁
7190d50b27 update 2024-07-01 17:38:55 +08:00
游雁
392a93d919 update 2024-07-01 16:08:39 +08:00
游雁
499daf0e8e update 2024-07-01 14:20:09 +08:00
游雁
3670095d21 Merge branch 'dev_gzf_deepspeed' of github.com:alibaba-damo-academy/FunASR into dev_gzf_deepspeed
merge
2024-07-01 11:25:56 +08:00
zhifu gao
60d9fa21dd
update with main (#1862)
* 优化merge segments 参数,解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)

* update

* v1.0.29

---------

Co-authored-by: wuhongsheng <664116298@qq.com>
2024-07-01 11:13:17 +08:00
游雁
b5ad25bce3 Merge branch 'dev_gzf_deepspeed' of github.com:alibaba-damo-academy/FunASR into dev_gzf_deepspeed
merge
2024-06-28 17:30:14 +08:00
zhifu gao
8c87a9d8a7
Dev gzf deepspeed (#1858)
* total_time/accum_grad

* fp16

* update with main (#1817)

* add cmakelist

* add paraformer-torch

* add debug for funasr-onnx-offline

* fix redefinition of jieba StdExtension.hpp

* add loading torch models

* update funasr-onnx-offline

* add SwitchArg for wss-server

* add SwitchArg for funasr-onnx-offline

* update cmakelist

* update funasr-onnx-offline-rtf

* add define condition

* add gpu define for offlne-stream

* update com define

* update offline-stream

* update cmakelist

* update func CompileHotwordEmbedding

* add timestamp for paraformer-torch

* add C10_USE_GLOG for paraformer-torch

* update paraformer-torch

* fix func FunASRWfstDecoderInit

* update model.h

* fix func FunASRWfstDecoderInit

* fix tpass_stream

* update paraformer-torch

* add bladedisc for funasr-onnx-offline

* update comdefine

* update funasr-wss-server

* add log for torch

* fix GetValue BLADEDISC

* fix log

* update cmakelist

* update warmup to 10

* update funasrruntime

* add batch_size for wss-server

* add batch for bins

* add batch for offline-stream

* add batch for paraformer

* add batch for offline-stream

* fix func SetBatchSize

* add SetBatchSize for model

* add SetBatchSize for model

* fix func Forward

* fix padding

* update funasrruntime

* add dec reset for batch

* set batch default value

* add argv for CutSplit

* sort frame_queue

* sorted msgs

* fix FunOfflineInfer

* add dynamic batch for fetch

* fix FetchDynamic

* update run_server.sh

* update run_server.sh

* cpp http post server support (#1739)

* add cpp http server

* add some comment

* remove some comments

* del debug infos

* restore run_server.sh

* adapt to new model struct

* 修复了onnxruntime在macos下编译失败的错误 (#1748)

* Add files via upload

增加macos的编译支持

* Add files via upload

增加macos支持

* Add files via upload

target_link_directories(funasr PUBLIC ${ONNXRUNTIME_DIR}/lib)
target_link_directories(funasr PUBLIC ${FFMPEG_DIR}/lib)
添加 if(APPLE) 限制

---------

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

* Delete docs/images/wechat.png

* Add files via upload

* fixed the issues about seaco-onnx timestamp

* fix bug (#1764)

当语音识别结果包含 `http` 时,标点符号预测会把它会被当成 url

* fix empty asr result (#1765)

解码结果为空的语音片段,text 用空字符串

* update export

* update export

* docs

* docs

* update export name

* docs

* update

* docs

* docs

* keep empty speech result (#1772)

* docs

* docs

* update wechat QRcode

* Add python funasr api support for websocket srv (#1777)

* add python funasr_api supoort

* change little to README.md

* add core tools stream

* modified a little

* fix bug for timeout

* support for buffer decode

* add ffmpeg decode for buffer

* libtorch demo

* update libtorch infer

* update utils

* update demo

* update demo

* update libtorch inference

* update model class

* update seaco paraformer

* bug fix

* bug fix

* auto frontend

* auto frontend

* auto frontend

* auto frontend

* auto frontend

* auto frontend

* auto frontend

* auto frontend

* Dev gzf exp (#1785)

* resume from step

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* train_loss_avg train_acc_avg

* train_loss_avg train_acc_avg

* train_loss_avg train_acc_avg

* log step

* wav is not exist

* wav is not exist

* decoding

* decoding

* decoding

* wechat

* decoding key

* decoding key

* decoding key

* decoding key

* decoding key

* decoding key

* dynamic batch

* start_data_split_i=0

* total_time/accum_grad

* total_time/accum_grad

* total_time/accum_grad

* update avg slice

* update avg slice

* sensevoice sanm

* sensevoice sanm

* sensevoice sanm

---------

Co-authored-by: 北念 <lzr265946@alibaba-inc.com>

* auto frontend

* update paraformer timestamp

* [Optimization] support bladedisc fp16 optimization (#1790)

* add cif_v1 and cif_export

* Update SDK_advanced_guide_offline_zh.md

* add cif_wo_hidden_v1

* [fix] fix empty asr result (#1794)

* english timestamp for valilla paraformer

* wechat

* [fix] better solution for handling empty result (#1796)

* update scripts

* modify the qformer adaptor (#1804)

Co-authored-by: nichongjia-2007 <nichongjia@gmail.com>

* add ctc inference code (#1806)

Co-authored-by: haoneng.lhn <haoneng.lhn@alibaba-inc.com>

* Update auto_model.py

修复空字串进入speaker model时报raw_text变量不存在的bug

* Update auto_model.py

修复识别出空串后spk_model内变量未定义问题

* update model name

* fix paramter 'quantize' unused issue (#1813)

Co-authored-by: ZihanLiao <liaozihan1@xdf.cn>

* wechat

* Update cif_predictor.py (#1811)

* Update cif_predictor.py

* modify cif_v1_export

under extreme cases, max_label_len calculated by batch_len misaligns with token_num

* Update cif_predictor.py

torch.cumsum precision degradation, using float64 instead

* update code

---------

Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com>
Co-authored-by: zhaomingwork <61895407+zhaomingwork@users.noreply.github.com>
Co-authored-by: szsteven008 <97944818+szsteven008@users.noreply.github.com>
Co-authored-by: Ephemeroptera <605686962@qq.com>
Co-authored-by: 彭震东 <zhendong.peng@qq.com>
Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
Co-authored-by: 北念 <lzr265946@alibaba-inc.com>
Co-authored-by: xiaowan0322 <wanchen.swc@alibaba-inc.com>
Co-authored-by: zhuangzhong <zhuangzhong@corp.netease.com>
Co-authored-by: Xingchen Song(宋星辰) <xingchensong1996@163.com>
Co-authored-by: nichongjia-2007 <nichongjia@gmail.com>
Co-authored-by: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Co-authored-by: liugz18 <57401541+liugz18@users.noreply.github.com>
Co-authored-by: Marlowe <54339989+ZihanLiao@users.noreply.github.com>
Co-authored-by: ZihanLiao <liaozihan1@xdf.cn>
Co-authored-by: zhong zhuang <zhuangz@lamda.nju.edu.cn>

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* v1.0.28 (#1836)

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* update (#1841)

* v1.0.28

* version checker

* version checker

* rollback cif_v1 for training bug

* fixbug

* fixbug for cif

* fixbug

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>

* update (#1842)

* v1.0.28

* version checker

* version checker

* rollback cif_v1 for training bug

* fixbug

* fixbug for cif

* fixbug

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>

* inference

* inference

* inference

* requests

* finetune

* finetune

* finetune

* finetune

* finetune

* add inference prepare func (#1848)

* docs

* docs

* docs

* docs

* docs

---------

Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com>
Co-authored-by: zhaomingwork <61895407+zhaomingwork@users.noreply.github.com>
Co-authored-by: szsteven008 <97944818+szsteven008@users.noreply.github.com>
Co-authored-by: Ephemeroptera <605686962@qq.com>
Co-authored-by: 彭震东 <zhendong.peng@qq.com>
Co-authored-by: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
Co-authored-by: 北念 <lzr265946@alibaba-inc.com>
Co-authored-by: xiaowan0322 <wanchen.swc@alibaba-inc.com>
Co-authored-by: zhuangzhong <zhuangzhong@corp.netease.com>
Co-authored-by: Xingchen Song(宋星辰) <xingchensong1996@163.com>
Co-authored-by: nichongjia-2007 <nichongjia@gmail.com>
Co-authored-by: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Co-authored-by: liugz18 <57401541+liugz18@users.noreply.github.com>
Co-authored-by: Marlowe <54339989+ZihanLiao@users.noreply.github.com>
Co-authored-by: ZihanLiao <liaozihan1@xdf.cn>
Co-authored-by: zhong zhuang <zhuangz@lamda.nju.edu.cn>
Co-authored-by: PerfeZ <90945395+PerfeZ@users.noreply.github.com>
2024-06-28 17:28:09 +08:00
游雁
6d8c7a0477 docs 2024-06-28 17:27:17 +08:00
游雁
7651863d16 docs 2024-06-28 17:24:13 +08:00
雾聪
e78d649ddb update readme 2024-06-28 14:28:43 +08:00
雾聪
f170a8e07f update readme 2024-06-28 11:12:07 +08:00
维石
c3ec6b9b9e update cif export 2024-06-28 10:24:54 +08:00
lingji-yidong
c880db5364
Fix: Return tuple ('', []) when char_list is empty to prevent ValueError (#1857)
This commit fixes an issue where an empty char_list causes a ValueError due to insufficient values to unpack. The function now returns a tuple ('', []) when char_list is empty.
2024-06-28 01:28:24 +08:00
游雁
02870bdb15 docs 2024-06-28 00:34:00 +08:00
雾聪
3c50a034b2 update sdk_roadmap.jpg 2024-06-27 17:49:33 +08:00
Yabin Li
d9529818f5
Add files via upload 2024-06-27 17:44:55 +08:00
Yabin Li
5853ebc98f
Merge Dev blade (#1856)
* update readme

* add benchmark_libtorch_cpp

* add benchmark_libtorch_cpp

* update readme

* update readme

* update readme

* update readme
2024-06-27 17:38:19 +08:00
游雁
196dae52a3 docs 2024-06-27 10:13:07 +08:00
游雁
33591ef555 Merge branch 'dev_gzf_deepspeed' of github.com:alibaba-damo-academy/FunASR into dev_gzf_deepspeed
merge
2024-06-26 17:03:59 +08:00
游雁
42591b4f1d docs 2024-06-26 17:03:31 +08:00
PerfeZ
e3eb52f8bf
add inference prepare func (#1848) 2024-06-26 15:35:31 +08:00
雾聪
38c1f6393a add warmup for paraformer-torch 2024-06-26 11:39:19 +08:00
游雁
d9bdd0eb67 finetune 2024-06-25 23:57:40 +08:00
游雁
f1e463606d finetune 2024-06-25 23:53:41 +08:00
游雁
d198a09ee9 finetune 2024-06-25 22:22:41 +08:00
游雁
290ac245bd finetune 2024-06-25 21:39:10 +08:00
游雁
1cbd2015f0 finetune 2024-06-25 20:43:08 +08:00