Commit Graph

101 Commits

Author SHA1 Message Date
游雁
83d644c899 decoding 2024-06-12 19:47:53 +08:00
游雁
2ac79cd3f3 decoding 2024-06-12 19:27:35 +08:00
游雁
e4a69d4768 decoding 2024-06-12 19:17:55 +08:00
游雁
765e6371bb decoding 2024-06-12 16:48:15 +08:00
游雁
6a74eb706c decoding 2024-06-12 15:45:03 +08:00
游雁
407625a734 decoding 2024-06-12 15:18:42 +08:00
游雁
a56980a26f decoding 2024-06-12 14:49:24 +08:00
游雁
9ec4f8c629 decoding 2024-06-12 14:43:59 +08:00
游雁
be26169447 decoding 2024-06-12 14:00:34 +08:00
游雁
1c8b46a233 fix bug 2024-06-09 00:21:44 +08:00
游雁
64941d99cc auto frontend 2024-06-06 19:48:40 +08:00
游雁
524237d759 auto frontend 2024-06-06 18:53:10 +08:00
游雁
9633e64bb1 auto frontend 2024-06-06 18:46:29 +08:00
zhifu gao
32e7836645
update with main (#1786)
* 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

* docs

* docs

* docs

* 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

* 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

---------

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>
2024-06-06 09:54:35 +08:00
zhifu gao
963ba1a771
Dev gzf deepspeed (#1737)
* 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

* add

* add

* add

* add

* deepspeed

* update with main (#1731)

* c++ runtime adapt to 1.0 (#1724)

* adapt vad runtime to 1.0

* add json

* change yml name

* add func LoadVocabFromJson

* add token file for InitAsr

* add token path for OfflineStream

* add funcOpenYaml

* add token file for InitPunc

* add token file for stream

* update punc-model

* update funasr-wss-server

* update runtime_sdk_download_tool.py

* update docker list

* Delete docs/images/wechat.png

* Add files via upload

* Emo2Vec限定选择的情感类别 (#1730)

* 限定选择的情感类别

* 使用none来禁用情感标签输出

* 修改输出接口

* 使用unuse来禁用token

---------

Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>

* bugfix

* v1.0.27

* update docs

* hf hub

* Fix incorrect assignment of 'end' attribute to 'start' in sentences list comprehension (#1680)

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com>

* docs

* docs

* deepspeed

* deepspeed

* deepspeed

* deepspeed

* update

* ds

* ds

* ds

* ds

* ds

* ds

* ds

* add

* add

* bugfix

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com>
2024-05-20 17:11:41 +08:00
zhifu gao
961ec280af
Dev gzf deepspeed (#1736)
* 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

* add

* add

* add

* add

* deepspeed

* update with main (#1731)

* c++ runtime adapt to 1.0 (#1724)

* adapt vad runtime to 1.0

* add json

* change yml name

* add func LoadVocabFromJson

* add token file for InitAsr

* add token path for OfflineStream

* add funcOpenYaml

* add token file for InitPunc

* add token file for stream

* update punc-model

* update funasr-wss-server

* update runtime_sdk_download_tool.py

* update docker list

* Delete docs/images/wechat.png

* Add files via upload

* Emo2Vec限定选择的情感类别 (#1730)

* 限定选择的情感类别

* 使用none来禁用情感标签输出

* 修改输出接口

* 使用unuse来禁用token

---------

Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>

* bugfix

* v1.0.27

* update docs

* hf hub

* Fix incorrect assignment of 'end' attribute to 'start' in sentences list comprehension (#1680)

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com>

* docs

* docs

* deepspeed

* deepspeed

* deepspeed

* deepspeed

* update

* ds

* ds

* ds

* ds

* ds

* ds

* ds

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com>
2024-05-20 15:31:46 +08:00
zhifu gao
a0f03bd2a8
Dev gzf deepspeed (#1732)
* 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

* add

* add

* add

* add

* deepspeed

* update with main (#1731)

* c++ runtime adapt to 1.0 (#1724)

* adapt vad runtime to 1.0

* add json

* change yml name

* add func LoadVocabFromJson

* add token file for InitAsr

* add token path for OfflineStream

* add funcOpenYaml

* add token file for InitPunc

* add token file for stream

* update punc-model

* update funasr-wss-server

* update runtime_sdk_download_tool.py

* update docker list

* Delete docs/images/wechat.png

* Add files via upload

* Emo2Vec限定选择的情感类别 (#1730)

* 限定选择的情感类别

* 使用none来禁用情感标签输出

* 修改输出接口

* 使用unuse来禁用token

---------

Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>

* bugfix

* v1.0.27

* update docs

* hf hub

* Fix incorrect assignment of 'end' attribute to 'start' in sentences list comprehension (#1680)

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com>

* docs

---------

Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com>
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com>
2024-05-15 19:48:50 +08:00
zhifu gao
00d0df3a10
Dev gzf decoding (#1695)
* 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
2024-05-06 22:17:25 +08:00
zhifu gao
48a8c95334
Dev gzf exp (#1684)
* 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
2024-04-30 16:28:02 +08:00
zhifu gao
a09aba419f
Dev gzf exp (#1682)
* resume from step
2024-04-30 12:52:58 +08:00
zhifu gao
b7ae3d5268
Dev gzf exp (#1672)
* resume from step

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch
2024-04-28 17:42:33 +08:00
zhifu gao
93ef505e2d
Dev gzf exp (#1670)
* resume from step

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch

* batch
2024-04-28 15:14:57 +08:00
zhifu gao
fc68b5ffe4
Dev gzf exp (#1661)
* rwkv 5

* rwkv v4

* rwkv v4

* rwkv

* rwkv

* update

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step

* resume from step
2024-04-25 21:43:47 +08:00
zhifu gao
80bd14e6bb
Dev gzf exp (#1657)
* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* bugfix

* update with main (#1631)

* update seaco finetune

* v1.0.24

---------

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

* sensevoice

* sensevoice

* sensevoice

* update with main (#1638)

* update seaco finetune

* v1.0.24

* update rwkv template

---------

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

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* whisper

* whisper

* update style

* update style

* oom

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-25 10:41:14 +08:00
zhifu gao
861147c730
Dev gzf exp (#1654)
* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* bugfix

* update with main (#1631)

* update seaco finetune

* v1.0.24

---------

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

* sensevoice

* sensevoice

* sensevoice

* update with main (#1638)

* update seaco finetune

* v1.0.24

* update rwkv template

---------

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

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* whisper

* whisper

* update style

* update style

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-24 16:03:38 +08:00
zhifu gao
2ac38adbe5
Dev gzf exp (#1647)
* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* bugfix

* update with main (#1631)

* update seaco finetune

* v1.0.24

---------

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

* sensevoice

* sensevoice

* sensevoice

* update with main (#1638)

* update seaco finetune

* v1.0.24

* update rwkv template

---------

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

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-23 18:08:57 +08:00
zhifu gao
824377d2aa
Dev gzf exp (#1626)
* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune
2024-04-17 16:59:29 +08:00
zhifu gao
6fa8ee48e1
Dev gzf new (#1567)
* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* whisper_lib for sense voice

* aishell recipe
2024-03-30 10:13:42 +08:00
zhifu gao
f5f8f81ce9
Dev gzf new (#1561)
* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train
2024-03-29 09:59:34 +08:00
zhifu gao
2297d7515a
Dev gzf new (#1553)
* train

* train

* train

* train

* train

* train

* train

* train
2024-03-27 23:20:53 +08:00
zhifu gao
16c70d831d
Dev gzf new (#1551)
* train

* train
2024-03-27 18:39:46 +08:00
zhifu gao
db82796f95
train (#1548) 2024-03-27 17:23:13 +08:00
游雁
08392f28ec train 2024-03-27 17:06:26 +08:00
游雁
06eb999835 train 2024-03-27 16:53:57 +08:00
游雁
3d19549d2e bugfix seg_dict_file 2024-03-27 16:30:05 +08:00
游雁
9b4e9cc8a0 train update 2024-03-27 16:05:29 +08:00
游雁
507f821d7a update 2024-03-26 16:45:10 +08:00
游雁
56305d84e3 update 2024-03-26 16:24:40 +08:00
游雁
ed952ff630 finetune 2024-03-24 15:11:02 +08:00
游雁
ed22e34d65 finetune 2024-03-24 15:03:54 +08:00
游雁
a70f5b3edf finetune 2024-03-24 01:44:18 +08:00
游雁
16a976a01d finetune 2024-03-24 01:27:08 +08:00
游雁
5d74e107fc update 2024-03-24 00:58:56 +08:00
游雁
873cfae5c3 update 2024-03-24 00:45:45 +08:00
游雁
fffb628d31 update 2024-03-22 22:51:11 +08:00
游雁
6ce4909ecc update 2024-03-22 21:08:55 +08:00
游雁
334422ead3 update 2024-03-22 20:35:58 +08:00
zhifu gao
4482bbcbb9
train (#1521)
* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer
2024-03-21 11:49:30 +08:00
zhifu gao
3ac03e448b
train & finetune llm-asr (#1519)
* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer
2024-03-21 01:36:39 +08:00
游雁
d3d2fe73c0 wav fronend 2024-03-18 20:46:23 +08:00