{
 "id": "FBK-MT/mosel",
 "owner": "FBK-MT",
 "name": "mosel",
 "downloads": 3876,
 "likes": 93,
 "last_modified": "2025-10-07T08:07:55.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition",
  "text-to-speech"
 ],
 "citation": "@inproceedings{mosel,\n  title = {{MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages}},\n  author = {Marco Gaido and Sara Papi and Luisa Bentivogli and Alessio Brutti and Mauro Cettolo and Roberto Gretter and Marco Matassoni and Mohamed Nabih and Matteo Negri},\n  booktitle = \"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing\",\n  month = nov,\n  year = \"2024\",\n  address = \"Miami, United States\",\n  publisher = \"Association for Computational Linguistics\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "40d224f5d6d61246ab80c369c21405c24952bbf1",
 "stated_evidence": "https://huggingface.co/datasets/FBK-MT/mosel/blob/40d224f5d6d61246ab80c369c21405c24952bbf1/README.md",
 "file_evidence": "https://huggingface.co/datasets/FBK-MT/mosel/tree/40d224f5d6d61246ab80c369c21405c24952bbf1",
 "card_nc": false
}