{
 "id": "lab260/Balalaika-longform",
 "owner": "lab260",
 "name": "Balalaika-longform",
 "downloads": 232,
 "likes": 0,
 "last_modified": "2026-09-15T13:45:30.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "creative-commons-attribution-source-licenses",
 "licence_link": "LICENSE.md",
 "file_licence": "cc-by-3.0",
 "licence_files": [
  "LICENSE.md"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-to-speech"
 ],
 "citation": "**All source videos in this release were marked Creative Commons Attribution on YouTube in the archived metadata.** This is supported by a catalog `cc: true` flag, a saved YouTube `Creative Commons Attribution license (reuse allowed)` value, or both. These records were checked for all 313 included source videos when building the release; no conflicting or unknown license flag was accepted.\n\nThe source recordings retain their source licenses. Preserve the original video title, creator/channel attribution where available, source link, and licensing information when redistributing samples, and indicate the segmentation and speech enhancement applied here. The per-sample `source` object and [source index](metadata/sources.jsonl) provide this provenance. See [YouTube's Creative Commons documentation](https://support.google.com/youtube/answer/2797468?hl=en) and [LICENSE.md](LICENSE.md).\n\nThe archived flags identify the CC BY license family without a version number. This release therefore preserves the source declaration instead of assigning a new CC version to every recording. The uploader-provided flag is licensing evidence, not an independent rights audit of every underlying text or performance.\n\nFor attribution corrections or removal requests, open a [dataset discussion](https://huggingface.co/datasets/lab260/Balalaika-longform/discussions) and include the relevant video URL or sample ID.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "96a1abc07caf80703e4dc0578aadb4e43811398d",
 "stated_evidence": "https://huggingface.co/datasets/lab260/Balalaika-longform/blob/96a1abc07caf80703e4dc0578aadb4e43811398d/README.md",
 "file_evidence": "https://huggingface.co/datasets/lab260/Balalaika-longform/blob/96a1abc07caf80703e4dc0578aadb4e43811398d/LICENSE.md",
 "card_nc": false
}