README.md

metadata

title: SenseVoice
emoji: 🎙️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.9.1
app_file: app.py
pinned: true
license: other
suggested_hardware: zero-a10g

SenseVoice: Speech Recognition + Emotion + Audio Events

Multi-task speech understanding model supporting 5 languages (zh/en/yue/ja/ko) with emotion detection and audio event recognition. 7x faster than Whisper-small.

• GitHub: SenseVoice | FunASR
• Paper: arXiv:2407.04051