mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 867k • 878
Generate animatable 3D models from mesh files
Visualize LeRobot datasets with interactive charts and tools
Embedded MinerU document extraction demo
Detect human poses in images and videos
Text-to-3D and Image-to-3D Generation
Image-to-3D Generation
VGGT (CVPR 2025)