{
 "id": "picheny/ccu-hf-data",
 "owner": "picheny",
 "name": "ccu-hf-data",
 "downloads": 616,
 "likes": 0,
 "last_modified": "2026-05-05T16:31:06.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "creative-commons-filtered-subset",
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "license_he_filtered.csv",
  "license_ko_filtered.csv",
  "license_tr_filtered.csv",
  "license_zh_filtered.csv"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition"
 ],
 "citation": "When using or redistributing items from this dataset, please credit each item as:\n\n> *\"[title]\"* by [uploader] ([uploader_id]), [webpage_url],\n> licensed under Creative Commons Attribution (reuse allowed)\n> *(or: license unconfirmed, selected via YouTube CC filter)*.\n> Audio extracted, segmented, and transcripts cleaned for speech research.\n\nSee [ATTRIBUTION.txt](ATTRIBUTION.txt) for additional information and  per-language breakdown.\n\nIf you use this dataset, please cite this dataset page and acknowledge the original source creators listed in attribution files.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "38103b7e3f62f8477f72e840cba28bba24fdb711",
 "stated_evidence": "https://huggingface.co/datasets/picheny/ccu-hf-data/blob/38103b7e3f62f8477f72e840cba28bba24fdb711/README.md",
 "file_evidence": "https://huggingface.co/datasets/picheny/ccu-hf-data/blob/38103b7e3f62f8477f72e840cba28bba24fdb711/license_he_filtered.csv",
 "card_nc": false
}