
espnet/owls_4B_180K
Automatic Speech Recognition
•
Updated
•
51
•
4
Describe math images and answer questions
Easily expand image boundaries
Generate depth maps from images
Generate surface normals from images
Generate customized images using text and an ID image
Generate speech from text
Compute normals for images and videos
Create high-quality HD cutouts with just a text prompt
Segment body parts in images
Engage in multi-modal conversations with images and videos
Generate responses from text and images