冯杨 / liveTalking

语音服务介绍

该服务以modelscope funasr语音识别为基础

Install

pip install torch -i https://mirrors.aliyun.com/pypi/simple/ pip install modelscope -i https://mirrors.aliyun.com/pypi/simple/ pip install testresources -i https://mirrors.aliyun.com/pypi/simple/ pip install websockets -i https://mirrors.aliyun.com/pypi/simple/ pip install torchaudio -i https://mirrors.aliyun.com/pypi/simple/ pip install FunASR -i https://mirrors.aliyun.com/pypi/simple/

Start server

2、python -u ASR_server.py --host "0.0.0.0" --port 10197 --ngpu 0

Fay connect

更改fay/system.conf配置项，并重新启动fay.

https://www.bilibili.com/video/BV1qs4y1g74e/?share_source=copy_web&vd_source=64cd9062f5046acba398177b62bea9ad

Acknowledge

感谢

1. 中科大脑算法工程师张聪聪
2. cgisky1980
3. modelscope
4. FunASR
5. Fay数字人助理.

---

GPU服务器部署： GPU服务器局域网地址：10.110.3.219 可用GPU：1号GPU python -u ASR_server.py --host "10.110.3.219" --port 10197 --ngpu 1 --gpu_id 1

python -u ASR_server.py --host "127.0.0.1" --port 10197 --ngpu 1

lsof -i :10197

#!/bin/bash source /home/fengyang/anaconda3/bin/activate livetalking

nohup python /home/fengyang/controlPanel/main.py >> /home/fengyang/controlPanel/panel_logfile.log 2>&1 &

chmod +x serverFunasr.sh