OvisOCR2
🔎
104
Stream structured Markdown from document images and PDFs.
Stream structured Markdown from document images and PDFs.
Voice chat over WebSocket against a HF speech-to-speech
Talk to Gemma 4 face to face, with a 3D lip-synced avatar
Demo of the Collection of Qwen Image Edit LoRAs
Unified AR-LM-based speech enhancement & separation
Hy3 multi-turn streaming chat with function calling
Spotted text-to-speech with voice cloning and text-CFG