{
 "id": "kyutai/Babillage",
 "owner": "kyutai",
 "name": "Babillage",
 "downloads": 789,
 "likes": 14,
 "last_modified": "2025-03-21T11:47:30.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering"
 ],
 "citation": "@article{kyutai2025moshivis,\n  author = {Amélie Royer and Moritz Böhle and Gabriel de Marmiesse and\n  Laurent Mazaré and Alexandre Défossez and Neil Zeghidour and Patrick Pérez},\n  year = {2025},\n  title = {Vision-Speech Models: Teaching Speech Models to Converse about Images},\n  journal = {ArXiv},\n  url = {https://arxiv.org/abs/2503.15633}\n}\n\n@misc{babillage2025,\n  title={{Babillage: A Conversational and Spoken VQA Dataset}},\n  author = {Amélie Royer, Moritz Böhle, Gabriel de Marmiesse, Laurent Mazaré, Alexandre Défossez, Neil Zeghidour, Patrick Pérez},\n  year={2025},\n  url={https://huggingface.co/datasets/kyutai/babillage} \n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "3ede8566da87763fffe3e0a1d9b78cd76bf5b85d",
 "stated_evidence": "https://huggingface.co/datasets/kyutai/Babillage/blob/3ede8566da87763fffe3e0a1d9b78cd76bf5b85d/README.md",
 "file_evidence": "https://huggingface.co/datasets/kyutai/Babillage/tree/3ede8566da87763fffe3e0a1d9b78cd76bf5b85d",
 "card_nc": false
}