Home Projects Fun-ASR
Fun-ASR

Fun-ASR

by FunAudioLLM · GitHub

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

# 31-languages# asr# audio# audio-language-model
View on GitHub
⭐ Stars
1.4k
🍴 Forks
138
📜 License
Apache-2.0
Commercial use OK
📅 Created
2025
🔄 Last commit
6 days ago
🏷️ Category
31-languages
💻 Language
🖥️ Self-hostable
Likely
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Fun-ASR — GitHub preview card
📈 Star history
1 4091 408
2026-07-202026-07-21
📄 About

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

Frequently asked questions

What is Fun-ASR?

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

Is Fun-ASR open source?

Fun-ASR is an open-source project. It is released under the Apache-2.0 license.

Is Fun-ASR free?

Yes. Fun-ASR is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
OpenSourceAI badge — Fun-ASR

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=funaudiollm-fun-asr)](https://opensourceai.tech/project/funaudiollm-fun-asr.html)
More badge options →
🧬 Related projects🧬 View the DNA map →