FunAudioLLM/Fun-ASR-Nano

1---2title: Fun-ASR-Nano3emoji: 🚀4colorFrom: blue5colorTo: indigo6sdk: gradio7sdk_version: 5.23.08app_file: app.py9pinned: true10license: apache-2.011 12short_description: "LLM-powered ASR: 31 languages, Chinese dialects, timestamps"13---14 15# Fun-ASR-Nano: LLM-Powered Speech Recognition16 17End-to-end ASR model trained on tens of millions of hours, supporting **31 languages** including Chinese dialects (Cantonese, Sichuan, Shanghai, Minnan, etc.).18 19## Key Features20- 🌍 31 languages + Chinese dialect recognition21- 🎯 Native punctuation output (no post-processing needed)22- ⚡ Timestamps and speaker diarization support23- 🔥 Trained on massive multilingual data24 25## Links26- **GitHub**: [Fun-ASR](https://github.com/FunAudioLLM/Fun-ASR) | [FunASR Toolkit](https://github.com/modelscope/FunASR)27- **Model**: [Fun-ASR-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)28