{
 "id": "vezilka-ai/macedonian-speech",
 "owner": "vezilka-ai",
 "name": "macedonian-speech",
 "downloads": 1510,
 "likes": 0,
 "last_modified": "2026-10-27T23:22:59.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc0-1.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition"
 ],
 "citation": "The collection is distributed under CC-BY-4.0; `original_license` gives each clip's\nsource license (`finki-lectures` and `finki-benchmark` are CC0-1.0). Attribution for the\nCC-BY-4.0 sources: the Assembly of the Republic of North Macedonia (`parliament`) and the\nSYNDI project (`gostivar`, `ohrid`, `tikvesh`, `veles`). See `LICENSE` for each source's\nrights basis. Speaker identities, lecturer names, meeting ids and recording URLs are not\nreleased.\n\nNot included: the Vezilka Macedonian Audiobook Corpus (approval pending) and the\nconsented speech donations (consent audit pending).\n\n\nThe data article describing this collection (Gajdov, Karamachoski, Stojcheva, Mishkovski and Mishev, *Curated Macedonian speech datasets with regional transcription layers and a manually reviewed FINKI lecture benchmark*) is under review; its citation will be added here on publication.",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "10f821a517e25a1375e18f272854b8a0810017f7",
 "stated_evidence": "https://huggingface.co/datasets/vezilka-ai/macedonian-speech/blob/10f821a517e25a1375e18f272854b8a0810017f7/README.md",
 "file_evidence": "https://huggingface.co/datasets/vezilka-ai/macedonian-speech/blob/10f821a517e25a1375e18f272854b8a0810017f7/LICENSE",
 "card_nc": false
}