# streaming-sensevoice

**Repository Path**: zsljava/streaming-sensevoice

## Basic Information

- **Project Name**: streaming-sensevoice
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-09-05
- **Last Updated**: 2025-09-05

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# streaming-sensevoice

Streaming SenseVoice processes inference in chunks of [SenseVoice](https://github.com/FunAudioLLM/SenseVoice).

## Usage

- transcribe wav file

```bash
$ python main.py
```

![](images/screenshot.png)

- transcribe from microphone

```bash
$ python realtime.py
```

- transcribe from websocket

A basic WebSocket service built with [`Recorder`](https://github.com/xiangyuecn/Recorder) and `FastAPI`; the frontend uses `MP3` format to transmit audio information to reduce latency and increase stability.

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

# check cli options
python realtime_ws_server_demo.py --help
```