streaming-sensevoice

Quick setup

docker pull registry.cn-beijing.aliyuncs.com/gaofei_cangku/py310-gpu-fun-asr-nano-2512:20260106
docker run -it --gpus=all --net=host  --name=asr  --privileged=true  -v $PWD/:/data registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.2.1 bash
conda activate asr
pip install -r requirements.txt
pip install -r requirements-ws-demo.txt
python realtime_ws_server_demo.py 
前端访问：http://ip:9004即可

• 注意: Chrome 默认禁止非 HTTPS 网页使用麦克风。
• 解决: 需配置 chrome://flags/#unsafely-treat-insecure-origin-as-secure 才能使用麦克风。

效果不错

全文COPY：https://github.com/fengin/Fun-ASR-Nano-2512-Deploy

感谢作者，我只是部署了环境，测试了效果！！

以下为原作者内容：

Streaming SenseVoice processes inference in chunks of SenseVoice.

Usage

• transcribe wav file

$ python main.py

• transcribe from microphone

$ python realtime.py

• transcribe from websocket

A basic WebSocket service built with Recorder and FastAPI; the frontend uses MP3 format to transmit audio information to reduce latency and increase stability.

pip install -r requirements-ws-demo.txt
python realtime_ws_server_demo.py

# check cli options
python realtime_ws_server_demo.py --help