Rakancorle1

/

wvs-thud-model

like 2

Hi, I'm Niels from the Hugging Face community science team. This PR adds a model card for the paper When Vision Speaks for Sound.

The model card includes:

• Relevant metadata (pipeline_tag).
• Links to the paper, project page, and official GitHub repository.
• A summary of the model and the Thud framework.
• Citation information.

Please feel free to merge if this looks good!