8000 GitHub - trigrass2/ASR-LLM-TTS: This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three TTS models: CosyVoice, Edge-TTS, and pyttsx3
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
/ ASR-LLM-TTS Public
forked from ABexit/ASR-LLM-TTS

This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three TTS models: CosyVoice, Edge-TTS, and pyttsx3

License

Apache-2.0 license
0 stars 140 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

trigrass2/ASR-LLM-TTS

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
.github
.github
 
 
asset
asset
 
 
cosyvoice
cosyvoice
 
 
docker
docker
 
 
examples
examples
 
 
runtime/python
runtime/python
 
 
third_party/Matcha-TTS
third_party/Matcha-TTS
 
 
tools
tools
 
 
.gitignore
.gitignore
 
 
.gitmodules
.gitmodules
 
 
0_Inference_QWen2.5.py
0_Inference_QWen2.5.py
 
 
10_SenceVoice_QWen2.5_cosyVoice.py
10_SenceVoice_QWen2.5_cosyVoice.py
 
 
11_SenceVoice_QWen2.5_pytts3.py
11_SenceVoice_QWen2.5_pytts3.py
 
 
12_SenceVoice_QWen2.5_edgeTTS.py
12_SenceVoice_QWen2.5_edgeTTS.py
 
 
13_SenceVoice_QWen2.5_edgeTTS_realTime.py
13_SenceVoice_QWen2.5_edgeTTS_realTime.py
 
 
14_SenceVoice_QWen2VL_edgeTTS_realTime.py
14_SenceVoice_QWen2VL_edgeTTS_realTime.py
 
 
1_Inference_CosyVoice.py
1_Inference_CosyVoice.py
 
 
2_record_test.py
2_record_test.py
 
 
3_Inference_edgeTTS.py
3_Inference_edgeTTS.py
 
 
4_Inference_QWen2Audio.py
4_Inference_QWen2Audio.py
 
 
5_pyttsx3_test.py
5_pyttsx3_test.py
 
 
6_Inference_funasr.py
6_Inference_funasr.py
 
 
7.1_test_record_AV.py
7.1_test_record_AV.py
 
 
7.2_test_record_QWen2_VL_AV.py
7.2_test_record_QWen2_VL_AV.py
 
 
7.3_test_record_QWen2_VL_AV_TTS.py
7.3_test_record_QWen2_VL_AV_TTS.py
 
 
7.5_realTime_AV.py
7.5_realTime_AV.py
 
 
7.6_realTime_debug.py
7.6_realTime_debug.py
 
 
7.7_realTime_AV_multiImage.py
7.7_realTime_AV_multiImage.py
 
 
7.8_realTime_AV_video.py
7.8_realTime_AV_video.py
 
 
7_0_FunASR.py
7_0_FunASR.py
 
 
7_Inference_QWen2-VL.py
7_Inference_QWen2-VL.py
 
 
8_Inference_QWen2-VL_offline_AV.py
8_Inference_QWen2-VL_offline_AV.py
 
 
CODE_OF_CONDUCT.md
CODE_OF_CONDUCT.md
 
 
FAQ.md
FAQ.md
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 
README_CosyVoice.md
README_CosyVoice.md
 
 
environment.yml
environment.yml
 
 
requirements.txt
requirements.txt
 
 
webui.py
webui.py
 
 

Repository files navigation

241123， UPDATE 😄

单模态语音交互

13_SenceVoice_QWen2.5_edgeTTS_realTime.py

音视频多模态语音交互

14_SenceVoice_QWen2VL_edgeTTS_realTime.py

[演示demo,b站] (https://www.bilibili.com/video/BV1uQBCYrEYL)

语音交互大模型/SenceVoice-QWen2.5-TTS

框架

SenceVoice-QWen2.5-CosyVoice搭建

此工程主代码来于[CosyVoice] (https://github.com/FunAudioLLM/CosyVoice)

在CosyVoice基础上添加[SenceVoice] (https://github.com/modelscope/FunASR) 作为语音识别模型

添加[QWwn2.5] (https://github.com/QwenLM/Qwen2.5) 作为大语言模型进行对话理解

3种语音合成方法

CoosyVoice推理速度慢，严重影响对话实时性，额外添加pyttsx3和edgeTTS

EdgeTTS实验过程出现链接错误问题，升级版本至6.1.17解决，无需科学上网

All dependencies are listed in requirements.txt, the interactive inference scripts are 10/11/12_SenceVoice_QWen2.5_xxx.py.

Have fun! 😊

About

This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three TTS models: CosyVoice, Edge-TTS, and pyttsx3

Resources

Readme

License

Apache-2.0 license
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.4%
  • Dockerfile 0.6%
0