志浩
c2c1b66674
refine decoding process, merge flow and vocoder
2024-07-10 15:53:16 +08:00
志浩
e8861d71a5
refine decoding process, merge flow and vocoder
2024-07-10 12:55:22 +08:00
志浩
8d30c44144
refine decoding process, merge flow and vocoder
2024-07-10 12:49:57 +08:00
志浩
d64ba60f40
refine decoding process, merge flow and vocoder
2024-07-10 12:47:25 +08:00
志浩
8335712c66
refine decoding process, merge flow and vocoder
2024-07-10 11:49:42 +08:00
志浩
ffb553eb8e
refine decoding process, merge flow and vocoder
2024-07-10 11:37:10 +08:00
志浩
573ae881cd
refine decoding process, merge flow and vocoder
2024-07-10 11:17:33 +08:00
游雁
e49e54596c
update
2024-07-09 17:27:16 +08:00
游雁
6a69cae224
update
2024-07-09 09:33:54 +08:00
游雁
3fe8ff8f8c
update
2024-07-08 17:52:38 +08:00
游雁
d8d1cda2ee
update
2024-07-08 17:50:55 +08:00
游雁
498edc0791
update
2024-07-08 17:48:52 +08:00
游雁
037270ea44
update
2024-07-08 17:37:07 +08:00
游雁
259ea7523f
update
2024-07-08 16:05:35 +08:00
游雁
ef5ea9b05f
update
2024-07-08 14:32:58 +08:00
游雁
8f6d2787f0
update
2024-07-05 20:53:32 +08:00
游雁
496ca8eddb
update
2024-07-04 23:33:51 +08:00
游雁
e969be589e
update
2024-07-04 23:30:30 +08:00
游雁
256defef10
update
2024-07-04 13:04:45 +08:00
游雁
63800cb852
update
2024-07-04 11:07:27 +08:00
志浩
05acd675ec
add audio decoding
2024-07-04 10:37:36 +08:00
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
游雁
9d8a55c66a
update
2024-07-02 14:11:50 +08:00
游雁
4784baf2af
update
2024-07-02 14:10:57 +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
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
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
维石
c3ec6b9b9e
update cif export
2024-06-28 10:24:54 +08:00
Yabin Li
b7060884fa
Merge Dev tclas ( #1847 )
...
* support clas torchscripts
* fix CompileHotwordEmbedding
* add batch for tensor_hw_emb
* fix func of TimestampOnnx
* fix func of TimestampOnnx
* fix func of TimestampOnnx
* fix paraformer-torch fwd
* fix paraformer-torch fwd
* fix paraformer-torch fwd
* fix ~paraformer-torch
* update funasr-onnx-offline-rtf
* update funasr-onnx-offline-rtf
* update funasr-onnx-offline-rtf
* change tos model names
* fix results of ParaformerTorch::Forward
* fix results of ParaformerTorch::Forward
* add FusionStrategy for torch
* fix paraformer torch
* sync to main (#1826 )
* 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
* add
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* update export
* update export
* update export name
* update
* 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
* update with main (#1783 )
* 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
---------
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>
* 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 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>
* update paraformer timestamp
* auto frontend
* auto frontend
* [Optimization] support bladedisc fp16 optimization (#1790 )
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* add cif_v1 and cif_export
* auto frontend
* Update SDK_advanced_guide_offline_zh.md
* add cif_wo_hidden_v1
* auto frontend
* auto frontend
* auto frontend
* fix bug
* [fix] fix empty asr result (#1794 )
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* fp16
* english timestamp for valilla paraformer
* fp16
* wechat
* fixbug
* [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: 游雁 <zhifu.gzf@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>
Co-authored-by: 维石 <shixian.shi@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: 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>
* update runtime_sdk_download_tool
* update funasr-wss-server
* update vad_revision
* update funasr-wss-server
* update funasr-wss-server
* update punc quant
* rename torchscript
* Delete examples/industrial_data_pretraining/ctc/infer_from_local.py
* resolve conflicts
---------
Co-authored-by: 游雁 <zhifu.gzf@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>
Co-authored-by: 维石 <shixian.shi@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: 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>
2024-06-25 17:38:04 +08:00
zhifu gao
abb33d6b20
Dev gzf deepspeed ( #1844 )
...
* 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
---------
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>
2024-06-24 17:06:21 +08:00
Shi Xian
5b4363a3e1
Merge pull request #1838 from Chen1399/patch-1
...
Update export_meta.py
2024-06-24 10:44:11 +08:00
游雁
6afd105e75
fixbug
2024-06-24 10:20:05 +08:00
游雁
93f9a424f2
fixbug for cif
2024-06-24 10:07:31 +08:00
JIJIN CHEN
7649c9ef59
Update export_meta.py
...
err id for export embed onnx
2024-06-21 16:05:10 +08:00
维石
362eed972c
rollback cif_v1 for training bug
2024-06-21 15:21:33 +08:00
游雁
0df672a2d0
version checker
2024-06-21 11:28:50 +08:00
游雁
1c52e364aa
version checker
2024-06-21 11:19:19 +08:00
游雁
e6b259538b
v1.0.28
2024-06-21 10:45:51 +08:00
zhifu gao
61e4203fbf
sensevoice ( #1834 )
2024-06-20 17:14:29 +08:00
zhifu gao
e65b1f701a
Dev gzf deepspeed ( #1833 )
...
* 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
---------
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>
2024-06-20 17:09:33 +08:00
游雁
45d7aa9004
decoding
2024-06-19 10:26:40 +08:00
Shi Xian
6c467e6f0a
Merge pull request #1825 from modelscope/dev_libt
...
Dev libt
2024-06-18 10:01:56 +08:00
维石
9377eed41e
update code
2024-06-17 20:20:00 +08:00
游雁
72173314e1
decoding
2024-06-17 15:47:12 +08:00
游雁
7c4cfcfab4
decoding
2024-06-17 14:38:22 +08:00
游雁
c3da5ad097
Merge branch 'dev_gzf_deepspeed' of github.com:alibaba-damo-academy/FunASR into dev_gzf_deepspeed
...
merge
2024-06-17 14:09:28 +08:00
游雁
b01c9f1c25
decoding
2024-06-17 14:08:57 +08:00
北念
ada76b6312
sensevoice
2024-06-17 13:36:22 +08:00
Shi Xian
ba54c2f88f
Merge pull request #1809 from liugz18/main
...
修复识别出空串后spk_model内变量未定义问题
2024-06-17 11:11:25 +08:00
游雁
0033151b62
decoding
2024-06-17 00:55:42 +08:00
zhong zhuang
145022c438
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
2024-06-14 20:33:16 +08:00
游雁
08114ae27d
decoding
2024-06-14 15:16:40 +08:00
游雁
62ae998926
decoding
2024-06-14 14:44:11 +08:00
游雁
59bc02b089
decoding
2024-06-14 13:59:49 +08:00
游雁
67329a74a5
decoding
2024-06-14 11:04:49 +08:00
zhifu gao
fa3e835983
update with main ( #1816 )
...
* 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
* update paraformer timestamp
* 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 )
* 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>
* fix paramter 'quantize' unused issue (#1813 )
Co-authored-by: ZihanLiao <liaozihan1@xdf.cn>
---------
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: 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: Marlowe <54339989+ZihanLiao@users.noreply.github.com>
Co-authored-by: ZihanLiao <liaozihan1@xdf.cn>
2024-06-14 10:38:02 +08:00
游雁
47209220c6
decoding
2024-06-14 09:49:22 +08:00
游雁
70df8c97dd
decoding
2024-06-13 19:35:57 +08:00
游雁
5ebcba3d61
decoding
2024-06-13 19:16:19 +08:00
游雁
caf70826a6
decoding
2024-06-13 17:52:07 +08:00
游雁
d72df6cd2f
decoding
2024-06-13 17:45:33 +08:00
游雁
7355e20503
decoding
2024-06-13 17:40:40 +08:00
游雁
c553a8db17
decoding
2024-06-13 17:38:01 +08:00
游雁
664c400545
decoding
2024-06-13 16:59:40 +08:00
游雁
a1e18f808e
decoding
2024-06-13 16:22:09 +08:00
游雁
6ca0b838d4
decoding
2024-06-13 16:07:49 +08:00
游雁
5de8bfdcd8
decoding
2024-06-13 15:38:17 +08:00
游雁
e42c693f0b
decoding
2024-06-13 14:26:38 +08:00
游雁
5079d54595
decoding
2024-06-13 11:26:17 +08:00
游雁
a51234d426
decoding
2024-06-13 10:33:05 +08:00
游雁
dce53b268b
decoding
2024-06-13 09:56:44 +08:00
游雁
f97f3e8dd5
decoding
2024-06-13 09:52:10 +08:00
游雁
508ad6573a
decoding
2024-06-12 20:03:55 +08:00
游雁
f6cae2b48b
decoding
2024-06-12 19:53:59 +08:00
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
2518f03d20
decoding
2024-06-12 17:44:12 +08:00
游雁
9afcf0ea7d
decoding
2024-06-12 17:17:03 +08:00
维石
021035ef4d
update model name
2024-06-12 17:14:52 +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
liugz18
bac3ef2e25
Update auto_model.py
...
修复识别出空串后spk_model内变量未定义问题
2024-06-12 15:28:41 +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
7d57828086
decoding
2024-06-12 14:29:28 +08:00
游雁
be26169447
decoding
2024-06-12 14:00:34 +08:00
liugz18
648c03fdbb
Update auto_model.py
...
修复空字串进入speaker model时报raw_text变量不存在的bug
2024-06-12 12:30:00 +08:00
Shi Xian
1300d38bf0
Merge pull request #1801 from modelscope/dev_sx2
...
english timestamp for vanilla paraformer
2024-06-12 11:20:06 +08:00
zhifu gao
997374b88f
add ctc inference code ( #1806 )
...
Co-authored-by: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
2024-06-11 19:56:52 +08:00
游雁
05f05e7421
decoding
2024-06-11 19:00:55 +08:00
游雁
f57b3788f2
fixbug
2024-06-11 15:47:21 +08:00
zhifu gao
24af4286d5
modify the qformer adaptor ( #1804 )
...
Co-authored-by: nichongjia-2007 <nichongjia@gmail.com>
2024-06-11 15:26:35 +08:00
游雁
9e13f028bc
fixbug
2024-06-11 15:11:58 +08:00
R1ckShi
a0c58c8fc6
Merge branch 'dev_libt' of https://github.com/alibaba-damo-academy/FunASR into dev_libt
2024-06-11 14:41:24 +08:00
R1ckShi
0f1247d7a8
update scripts
2024-06-11 14:41:21 +08:00
游雁
779033386a
fixbug
2024-06-11 14:22:55 +08:00
zhifu gao
20aa07268a
update with main ( #1800 )
...
* 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
* update paraformer timestamp
* add cif_v1 and cif_export
* Update SDK_advanced_guide_offline_zh.md
* add cif_wo_hidden_v1
* [fix] fix empty asr result (#1794 )
* wechat
* [fix] better solution for handling empty result (#1796 )
---------
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: zhuangzhong <zhuangzhong@corp.netease.com>
Co-authored-by: Xingchen Song(宋星辰) <xingchensong1996@163.com>
2024-06-11 14:02:27 +08:00
zhifu gao
2175736ab0
Merge branch 'dev_gzf_deepspeed' into main
2024-06-11 14:02:18 +08:00
Xingchen Song(宋星辰)
0bd1a4d6a9
[fix] better solution for handling empty result ( #1796 )
2024-06-11 14:00:10 +08:00
游雁
a8653d897d
fixbug
2024-06-11 13:56:24 +08:00
游雁
63e60cc43d
fp16
2024-06-11 13:49:57 +08:00
维石
3e93192638
english timestamp for valilla paraformer
2024-06-11 11:52:26 +08:00
游雁
23008c7cac
fp16
2024-06-11 11:48:42 +08:00
Shi Xian
7a9c0414b6
Merge pull request #1791 from dtlzhuangz/zhuangzhong_dev
...
Accelerate cif
2024-06-11 11:42:15 +08:00
游雁
ea85c483ad
fix bug
2024-06-10 21:47:58 +08:00
游雁
7fc17b1aaf
fix bug
2024-06-09 22:40:49 +08:00
游雁
1d27a1507b
fix bug
2024-06-09 22:01:14 +08:00
游雁
281e9835b6
fix bug
2024-06-09 03:41:40 +08:00
游雁
373fbd15e0
fix bug
2024-06-09 03:36:23 +08:00
游雁
1163110135
fix bug
2024-06-09 03:29:41 +08:00
游雁
6e0d138826
fix bug
2024-06-09 03:26:32 +08:00
游雁
1186cd96a5
fix bug
2024-06-09 02:19:29 +08:00
游雁
3eee773814
fix bug
2024-06-09 02:11:42 +08:00
游雁
56986acaa7
fix bug
2024-06-09 02:05:49 +08:00
游雁
8bb9971753
fix bug
2024-06-09 01:35:15 +08:00
游雁
b75d1e89bb
fix bug
2024-06-09 00:32:57 +08:00
游雁
1c8b46a233
fix bug
2024-06-09 00:21:44 +08:00
游雁
2a8d041806
fix bug
2024-06-08 21:35:21 +08:00
游雁
9fd3c47fd7
fix bug
2024-06-08 21:08:54 +08:00
游雁
2191795f74
fix bug
2024-06-08 19:45:15 +08:00
游雁
3d5e19792c
fix bug
2024-06-08 18:43:35 +08:00
游雁
e5be285347
fix bug
2024-06-08 17:49:36 +08:00
游雁
310006dd60
fix bug
2024-06-08 17:19:32 +08:00
游雁
df00f5fc0b
fix bug
2024-06-08 16:54:14 +08:00
游雁
d94821bbd6
fix bug
2024-06-08 16:44:34 +08:00
Xingchen Song(宋星辰)
93a02feda1
[fix] fix empty asr result ( #1794 )
2024-06-07 23:10:13 +08:00
游雁
834a8fd9e2
auto frontend
2024-06-07 19:27:08 +08:00
游雁
526c810bd7
auto frontend
2024-06-07 18:44:14 +08:00
游雁
162efb747f
auto frontend
2024-06-07 16:18:18 +08:00
zhuangzhong
c367f1b819
add cif_wo_hidden_v1
2024-06-07 08:15:16 +00:00
游雁
8d7f76af46
auto frontend
2024-06-07 11:40:46 +08:00
zhuangzhong
e700341244
add cif_v1 and cif_export
2024-06-07 02:44:45 +00:00
游雁
c350b6becb
auto frontend
2024-06-07 04:32:26 +08:00
游雁
870fa4a37a
auto frontend
2024-06-07 04:05:30 +08:00
游雁
8ba12df6f7
auto frontend
2024-06-07 04:04:55 +08:00
游雁
d306728928
auto frontend
2024-06-07 03:34:41 +08:00
游雁
0ba1bdd476
auto frontend
2024-06-07 03:21:53 +08:00
游雁
a0becf3cd8
auto frontend
2024-06-07 03:13:36 +08:00
游雁
4eedd7ad45
auto frontend
2024-06-07 03:05:01 +08:00
游雁
b2be308de0
auto frontend
2024-06-07 02:51:18 +08:00
游雁
60b3c42d6d
auto frontend
2024-06-07 02:40:31 +08:00
游雁
4a99b828a8
auto frontend
2024-06-07 01:58:14 +08:00
游雁
64941d99cc
auto frontend
2024-06-06 19:48:40 +08:00
游雁
d6fedbfa77
auto frontend
2024-06-06 19:22:11 +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
游雁
e9acc5db07
auto frontend
2024-06-06 18:36:22 +08:00
xiaowan0322
9a9b474e7d
[Optimization] support bladedisc fp16 optimization ( #1790 )
2024-06-06 15:59:56 +08:00
游雁
27256ed429
auto frontend
2024-06-06 15:45:32 +08:00
维石
ce6b70e479
update paraformer timestamp
2024-06-06 10:08:17 +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
游雁
f64bbaa036
auto frontend
2024-06-06 01:16:48 +08:00
zhifu gao
db9ec58cb4
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>
2024-06-05 17:30:57 +08:00
游雁
79b09f1d67
auto frontend
2024-06-05 17:22:21 +08:00
游雁
a6441441cb
auto frontend
2024-06-05 16:54:33 +08:00
游雁
545d69ae92
auto frontend
2024-06-05 10:34:50 +08:00
游雁
46568227c9
auto frontend
2024-06-05 10:24:01 +08:00
游雁
2646018ddd
auto frontend
2024-06-05 09:52:46 +08:00
游雁
378eedbdc3
auto frontend
2024-06-05 09:31:56 +08:00
zhifu gao
3b0526e7be
update with main ( #1783 )
...
* 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
---------
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>
2024-06-04 11:21:36 +08:00
游雁
ddd4ad419b
auto frontend
2024-06-04 11:20:29 +08:00
游雁
1fcb757216
auto frontend
2024-06-03 17:13:48 +08:00
维石
f591f33111
update libtorch infer
2024-06-03 15:15:52 +08:00
彭震东
a64b7d8d8a
keep empty speech result ( #1772 )
2024-05-30 15:12:53 +08:00
R1ckShi
d097d0ca45
update
2024-05-30 14:59:07 +08:00
游雁
f577bb5e72
docs
2024-05-30 14:55:32 +08:00
维石
23eed38e9f
update export name
2024-05-30 14:22:32 +08:00
维石
64d7032073
update export
2024-05-28 19:09:03 +08:00
维石
e7351db81b
update export
2024-05-28 19:07:22 +08:00
彭震东
bd3b18016d
fix empty asr result ( #1765 )
...
解码结果为空的语音片段，text 用空字符串
2024-05-28 18:31:04 +08:00
Shi Xian
50b2668019
Merge pull request #1763 from coolEphemeroptera/main
...
fixed the issues about seaco-onnx timestamp
2024-05-28 17:46:30 +08:00
彭震东
2c4ae541e0
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
2024-05-28 17:11:38 +08:00
Ephemeroptera
18bbf145a0
fixed the issues about seaco-onnx timestamp
2024-05-28 15:55:20 +08:00
zhifu gao
f47d43c020
Dev gzf deepspeed ( #1750 )
...
* 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
* add
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
---------
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>
2024-05-23 09:57:14 +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
d3da0760a5
Dev gzf deepspeed ( #1733 )
...
* 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
---------
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>
2024-05-16 14:32:14 +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
游雁
fb45c9a6ef
hf hub
2024-05-15 17:32:07 +08:00
游雁
fffbefc28b
v1.0.27
2024-05-15 16:40:38 +08:00
游雁
c7bfd1fdc5
bugfix
2024-05-15 16:40:12 +08:00
gaochangfeng
2f7dcbad90
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>
2024-05-15 16:09:19 +08:00
root
ae04f1e6c0
update runtime_sdk_download_tool.py
2024-05-13 19:41:39 +08:00
游雁
be7cd2b538
v1.0.26
2024-05-08 19:23:52 +08:00
zhifu gao
4adb76a6ed
Dev gzf exp ( #1707 )
...
* 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
2024-05-08 19:21:58 +08:00
zhifu gao
a7bc099548
Dev gzf exp ( #1705 )
...
* 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
* Gcf (#1704 )
* 添加富文本解码约束
* special token
* bug fix
* fix
---------
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
* decoding key
---------
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
2024-05-08 17:32:36 +08:00
zhifu gao
b1c186fd00
Dev gzf exp ( #1700 )
...
* 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
2024-05-08 00:31:29 +08:00
zhifu gao
7be2a1d7e4
Dev gzf exp ( #1696 )
...
* 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
2024-05-06 22:36:00 +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
彭震东
1f49a4f2b2
fix single word case ( #1679 )
...
``` python
print(model.generate(input="是什么")[0]["text"])
```
2024-04-29 16:45:36 +08:00
zhifu gao
11cf10e433
Dev gzf exp ( #1678 )
...
* resume from step
* batch
* batch
* batch
2024-04-29 14:52:20 +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
1cdb3cc28d
Dev gzf exp ( #1665 )
...
* 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
* 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
2024-04-26 11:27:39 +08:00
zhifu gao
8fdc372c81
Dev gzf exp ( #1664 )
...
* 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
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
2024-04-26 01:37:29 +08:00
zhifu gao
e971e000ad
Dev gzf exp ( #1663 )
...
* 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
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
2024-04-26 01:11:18 +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
jianganghan
f8b4924060
fix bug for blank audio ( #1656 )
2024-04-25 10:42:19 +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
游雁
7c3ba91f67
v1.0.25
2024-04-23 20:18:54 +08:00
zhifu gao
26d642bfdf
Dev gzf exp ( #1651 )
...
* 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
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-23 20:13:44 +08:00
zhifu gao
61d631fb5b
Dev gzf exp ( #1650 )
...
* 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
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-23 19:51:32 +08:00
zhifu gao
8795bf5bf1
Dev gzf exp ( #1649 )
...
* 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
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-23 19:36:15 +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
0a4a1d5257
Dev gzf exp ( #1645 )
...
* 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
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-23 12:48:52 +08:00
querryton
01df8f330c
[fix] Fix a bug in seaco_paraformer model "inference" function ( #1639 )
2024-04-20 16:07:13 +08:00
维石
dee1354d0d
empty result bug fix
2024-04-19 14:57:31 +08:00
querryton
df768884a2
Update timestamp_tools.py
...
[fix] fix a bug in function "ts_prediction_lfr6_standard"
2024-04-19 13:37:05 +08:00
维石
8b03379434
update rwkv template
2024-04-19 11:25:25 +08:00
游雁
20caf531e6
v1.0.24
2024-04-18 14:37:38 +08:00
维石
3d12aa5674
update seaco finetune
2024-04-18 10:14:16 +08:00
zhifu gao
e8f80e96f9
Dev gzf exp ( #1627 )
...
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* bugfix
2024-04-17 21:23:20 +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
eaf9dda9e4
Dev gzf exp ( #1624 )
...
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
2024-04-17 15:05:37 +08:00
维石
149063ced4
update seaco finetune
2024-04-17 14:33:24 +08:00
游雁
199f6e630a
bugfix
2024-04-15 15:38:46 +08:00
游雁
90bc3ad02e
bugfix
2024-04-15 15:35:06 +08:00
游雁
27d2d3ccb7
add
2024-04-12 15:30:03 +08:00
游雁
da340e6a6c
add
2024-04-12 15:01:54 +08:00
gaochangfeng
3260fb879b
Dev gcf ( #1611 )
...
* 添加默认对Speech和BGM的输出格式约束
* 推理时可以合并vad的切分
* fix
---------
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
2024-04-12 11:37:22 +08:00
游雁
70027f0ead
add
2024-04-11 19:46:33 +08:00
gaochangfeng
fce4e1d1b4
SenseVoice对富文本解码的参数 ( #1608 )
...
* 修复无法预测nospeech标签的问题
* 修复prompt存储的设备的问题
* 添加增益事件的功能
* Debug测试通过，可以有效地增加掌声地召回率
* 增加情感阈值
* fix
* fix bug
---------
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: zhifu gao <zhifu.gzf@alibaba-inc.com>
2024-04-11 14:59:22 +08:00
gaochangfeng
851e3e3ef8
Gcf ( #1605 )
...
* 修复无法预测nospeech标签的问题
* 修复prompt存储的设备的问题
---------
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
Co-authored-by: zhifu gao <zhifu.gzf@alibaba-inc.com>
2024-04-10 14:37:35 +08:00
维石
b8bf792ce7
fix bug
2024-04-10 11:37:27 +08:00
zhifu gao
112c8e6eb7
修复无法预测nospeech标签的问题 ( #1604 )
...
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com>
2024-04-10 09:55:21 +08:00
Hui Wang
eef1c2a5b8
Update cluster_backend.py
...
update hdbscan api
2024-04-09 09:58:50 +08:00
