{
 "id": "henrygagnier/kazakh-ocr",
 "owner": "henrygagnier",
 "name": "kazakh-ocr",
 "downloads": 1492,
 "likes": 1,
 "last_modified": "2026-03-22T20:26:42.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-text-to-text",
  "image-to-text"
 ],
 "citation": "@inproceedings{gagnier-etal-2026-kazakhocr,\n    title = \"{K}azakh{OCR}: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource {K}azakh Script {OCR}\",\n    author = \"Gagnier, Henry  and\n      Gagnier, Sophie  and\n      Kirubakaran, Ashwin\",\n    booktitle = \"Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script\",\n    month = mar,\n    year = \"2026\",\n    address = \"Rabat, Morocco\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.abjadnlp-1.8/\",\n    pages = \"60--65\"",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "cf24690988e27bb6eacbb2c7ce8e78421021daf6",
 "stated_evidence": "https://huggingface.co/datasets/henrygagnier/kazakh-ocr/blob/cf24690988e27bb6eacbb2c7ce8e78421021daf6/README.md",
 "file_evidence": "https://huggingface.co/datasets/henrygagnier/kazakh-ocr/tree/cf24690988e27bb6eacbb2c7ce8e78421021daf6",
 "card_nc": false
}