{
 "id": "kurianbenoy/google-vaani-malayalam-subset",
 "owner": "kurianbenoy",
 "name": "google-vaani-malayalam-subset",
 "downloads": 112,
 "likes": 1,
 "last_modified": "2026-11-13T05:19:51.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "ARTPARK-IISc/VAANI",
   "licence": "cc-by-4.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/ARTPARK-IISc/Vaani/blob/9e6ed4f94f7060e633cbc500480623ae7521522c/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition",
  "audio-classification"
 ],
 "citation": "@inproceedings{vaani2025,\n  title     = {{VAANI}: A Large-Scale Multi-District, Multi-Dialect Speech Dataset for Indic Languages},\n  author    = {{AI4Bharat} and {ARTPARK-IISc}},\n  year      = {2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "2b525ce2b4663cb0919dbccb143c4139bf74933c",
 "stated_evidence": "https://huggingface.co/datasets/kurianbenoy/google-vaani-malayalam-subset/blob/2b525ce2b4663cb0919dbccb143c4139bf74933c/README.md",
 "file_evidence": "https://huggingface.co/datasets/kurianbenoy/google-vaani-malayalam-subset/tree/2b525ce2b4663cb0919dbccb143c4139bf74933c",
 "card_nc": false
}