{
 "id": "Ethosoft/Turkish_corpus",
 "owner": "Ethosoft",
 "name": "Turkish_corpus",
 "downloads": 1877,
 "likes": 1,
 "last_modified": "2026-04-24T17:00:32.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask",
  "sentence-similarity",
  "feature-extraction",
  "text-classification",
  "token-classification"
 ],
 "citation": "@dataset{ethosoft_turkish_corpus,\n  title = {Turkish Corpus},\n  author = {Ethosoft},\n  year = {2026},\n  note = {A cleaned Turkish text corpus collected from Turkish datasets and Turkish portions extracted from multilingual datasets.}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "c85caaa392cd5d7857c1e902f71a9910b13850c2",
 "stated_evidence": "https://huggingface.co/datasets/Ethosoft/Turkish_corpus/blob/c85caaa392cd5d7857c1e902f71a9910b13850c2/README.md",
 "file_evidence": "https://huggingface.co/datasets/Ethosoft/Turkish_corpus/tree/c85caaa392cd5d7857c1e902f71a9910b13850c2",
 "card_nc": false
}