Spaces:
Running on Zero
Running on Zero
| title: Fun-ASR-Nano GPU | |
| emoji: 🚀 | |
| colorFrom: blue | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 5.23.0 | |
| app_file: app.py | |
| pinned: true | |
| license: apache-2.0 | |
| suggested_hardware: zero-a10g | |
| short_description: "LLM-powered ASR on GPU: 31 languages, Chinese dialects" | |
| # Fun-ASR-Nano: LLM-Powered Speech Recognition (GPU) | |
| End-to-end ASR model trained on tens of millions of hours, supporting **31 languages** including Chinese dialects. | |
| ## Key Features | |
| - 🌍 31 languages + Chinese dialect recognition | |
| - 🎯 Native punctuation output | |
| - ⚡ GPU-accelerated inference via ZeroGPU | |
| - 🔥 Trained on massive multilingual data | |
| ## Links | |
| - **GitHub**: [Fun-ASR](https://github.com/FunAudioLLM/Fun-ASR) | [FunASR Toolkit](https://github.com/modelscope/FunASR) | |
| - **Model**: [Fun-ASR-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512) | |