Hi! I'm Niels from the Hugging Face community science team.
I'm opening this PR to improve the model card for Resp-Agent. Specifically, I've added the `audio-text-to-text` pipeline tag to the metadata to reflect the model's multimodal capabilities and improve discoverability. I've also added a link to the paper page on the Hugging Face Hub and ensured the GitHub repository link is correctly referenced. These changes help users better understand the context and usage of these model weights.
