---
id: "b904"
language: "en"
library: "tools"
official_url: "https://github.com/QwenAudio/Fun-ASR"
profile_updated_on: "2026-10-22"
---

# Fun-ASR

End-to-end ASR models: Nano focuses on Chinese, English, Japanese and Chinese dialects; MLT-Nano provides multilingual transcription through FunASR workflows.

- Company / organization: Alibaba Tongyi Lab
- Category: Speech recognition & input
- Official website: [https://github.com/QwenAudio/Fun-ASR](https://github.com/QwenAudio/Fun-ASR)
- Profile updated: 2026-10-22


## Overview

Fun-ASR is Tongyi Lab’s recognition-model family, distinct from the multi-model FunASR toolkit. Nano and MLT-Nano have different language scopes, with MLT-Nano targeting thirty-one languages. Direct, Transformers and FunASR workflows provide transcription, with hotwords and streaming depending on the runtime. Timestamps depend on the downloaded checkpoint, not its name alone; diarization needs additional models. Main code and the reviewed official Nano card declare Apache 2.0.

## Official sources and references

- [Official website](https://github.com/QwenAudio/Fun-ASR)
- [Documentation](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)

## Reading & subscriptions

- [Interactive profile](../../../products/fun-asr--b904.html)
- [Read](../../../read/en/products/fun-asr--b904.html)
- [JSON](../../../read/en/products/fun-asr--b904.json)

Descriptions summarize public information; consult official websites for features, pricing and regional availability.