FunASR

FunASR

Industrial-grade speech recognition toolkit supporting over 50 languages, speaker separation, and emotion detection.

MCPDevOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 18.5k
Source
mcp-github

Overview

FunASR is an industrial-grade speech recognition toolkit that supports over 50 languages and features speaker separation and emotion detection. It is 170 times faster than Whisper and provides an OpenAI-compatible API. With simple installation and invocation, it can be easily integrated into various AI applications. Ideal for developers and enterprises requiring high-performance speech processing capabilities.

Capabilities

  • Supports over 50 languages
  • Real-time speech recognition
  • Speaker separation
  • Emotion detection
  • Streaming processing
  • OpenAI-compatible API

Use cases

Multilingual speech-to-textAutomated meeting transcriptionEmotion analysisReal-time speech recognition

Setup

Requires: PyTorchtorchaudioGPU(推荐)
pip install torch torchaudio && pip install funasr

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How can I get started with FunASR quickly?

You can get started quickly via Colab or install locally and use the example code.

Which languages does FunASR support?

Supports over 50 languages, including Chinese, English, and more.

Do I need a GPU?

GPU is recommended for optimal performance, but CPU operation is also supported.

Related skills