{
 "id": "LEMAS-Project/LEMAS-Dataset-eval",
 "owner": "LEMAS-Project",
 "name": "LEMAS-Dataset-eval",
 "downloads": 898,
 "likes": 3,
 "last_modified": "2026-03-31T02:16:53.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-to-speech",
  "automatic-speech-recognition"
 ],
 "citation": "@article{zhao2026lemas,\n  title={LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models},\n  author={Zhao, Zhiyuan and Lin, Lijian and Zhu, Ye and Xie, Kai and Liu, Yunfei and Li, Yu},\n  journal={arXiv preprint arXiv:2601.04233},\n  year={2026}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "538d9af2c87251e83c8cdadb2a56d0c35a06c716",
 "stated_evidence": "https://huggingface.co/datasets/LEMAS-Project/LEMAS-Dataset-eval/blob/538d9af2c87251e83c8cdadb2a56d0c35a06c716/README.md",
 "file_evidence": "https://huggingface.co/datasets/LEMAS-Project/LEMAS-Dataset-eval/tree/538d9af2c87251e83c8cdadb2a56d0c35a06c716",
 "card_nc": false
}