{
 "id": "mabahboh/ArVoice-Undiacritized",
 "owner": "mabahboh",
 "name": "ArVoice-Undiacritized",
 "downloads": 480,
 "likes": 1,
 "last_modified": "2026-09-28T00:57:41.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [
  {
   "id": "MBZUAI/ArVoice",
   "licence": "cc-by-4.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/MBZUAI/ArVoice/blob/98ade23b24851329f0a528dac4edc0f453f71121/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-to-speech",
  "automatic-speech-recognition"
 ],
 "citation": "@inproceedings{toyin25_interspeech,\n  title     = {{ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis}},\n  author    = {Hawau Toyin and Rufael Marew and Humaid Alblooshi and Samar M. Magdy and Hanan Aldarmaki},\n  year      = {2025},\n  booktitle = {{Interspeech 2025}},\n  pages     = {4808--4812},\n  doi       = {10.21437/Interspeech.2025-1550},\n  issn      = {2958-1796},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "a806dafa42e3f4e3e52f89b2d4515689a7a1d6e6",
 "stated_evidence": "https://huggingface.co/datasets/mabahboh/ArVoice-Undiacritized/blob/a806dafa42e3f4e3e52f89b2d4515689a7a1d6e6/README.md",
 "file_evidence": "https://huggingface.co/datasets/mabahboh/ArVoice-Undiacritized/blob/a806dafa42e3f4e3e52f89b2d4515689a7a1d6e6/LICENSE",
 "card_nc": false
}