Audiosr Versatile Audio Super Resolution
📚
39
Versatile audio super resolution (any -> 48kHz) with AudioSR
The secrets to building world-class LLMs
Multimodal OCR model for complex document understanding.
Generate natural-sounding speech in European languages with voice cloning
Create 3D models from images using depth estimation
Decompose a 3D model into its individual parts
Generate realistic dialogue from a script, using Dia!