Verified project record

modelscope/FunASR

FunASR is an industrial-grade speech recognition toolkit for offline, streaming, and edge deployment of ASR, VAD, punctuation, speaker diarization, and emotion recognition tasks. It provides transcription across multiple languages and is designed as a faster, self-hostable alternative to Whisper and cloud APIs.

Project overview

Project type: MCP · Model Runtime · Audio & Speech
Use cases: Meeting Notes · Translation & Subtitles · Audio & Speech · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers, AI engineers, and researchers who need a self-hosted speech processing toolkit with built-in speaker, emotion, and VAD capabilities.

Key capabilities

Transcribes audio to text supporting various models for Chinese, English, Japanese, and up to 52 languages.
Processes audio in chunks for real-time transcription via WebSocket using Paraformer.
Identifies and segments speakers in audio using the CAM++ model.
Detects speech segments in audio using FSMN-VAD.
Adds punctuation to transcribed text using the ct-punc model.
Recognizes emotions in audio using SenseVoice or emotion2vec+large models.
Deploys an OpenAI-compatible /v1/audio/transcriptions endpoint via funasr-server.
Runs ASR as a single self-contained binary on CPU and edge devices without Python using llama.cpp and GGUF models.

Limitations and risks

Language support is checkpoint-specific and varies depending on the chosen model.
Pretrained model weights are licensed separately from the MIT toolkit source code.

Getting started

Setup difficulty is rated as easy. The first success path involves running 'pip install funasr' followed by executing 'funasr audio.wav' in the CLI.

Evidence and sources

README: Industrial speech recognition toolkit for offline, streaming, and edge deployment.
README: Whisper is a single model; **FunASR is a toolkit** — you pick the right model per job
README: Top speed | **340x realtime** (Fun-ASR-Nano + vLLM) | 13x realtime | ~1x realtime
README: - 2026/05/24: **vLLM Inference Engine** — 2-3x faster LLM decoding for Fun-ASR-Nano. Streaming WebSocket service with VAD + Speaker Diarization.
README: title={FunASR: A Fundamental End-to-End Speech Recognition Toolkit}

Reviewed at: 2026-07-17T12:02:14Z