Skip to content

A demo for Voice GPT, speech to text, text to LLM, text to speech running locally.

Notifications You must be signed in to change notification settings

WannaTen/echoGPT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

使用方法

Speech To Text 服务

使用faster-whisper-server

docker 部署即可:

docker run --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=large-v3 fedirz/faster-whisper-server:latest-cuda

Text to Speech 服务

使用ChatTTS-forge

Docker 部署:

git clone https://github.com/lenML/ChatTTS-Forge.git
cd ChatTTS-Forge
docker-compose -f ./docker-compose.api.yml up -d

使用

cd echoGPT
pip install -r requirement.txt
python main.py

ctrl + k 开始录音, 按 Esc 停止并发送语音, 等待模型生成文本, 并转录语音

About

A demo for Voice GPT, speech to text, text to LLM, text to speech running locally.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages