{
 "id": "Professor/yoruba-speech-data",
 "owner": "Professor",
 "name": "yoruba-speech-data",
 "downloads": 258,
 "likes": 3,
 "last_modified": "2026-10-17T20:09:33.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-to-speech",
  "automatic-speech-recognition"
 ],
 "citation": "@misc{datasciencenigeria_african_voices_2025,\n  title        = {African Voices: Multilingual Speech Dataset for Low-Resource African Languages},\n  author       = {DataScience Nigeria},\n  year         = {2025},\n  note         = {Latest release, November 2025},\n  howpublished = {\\url{https://www.africanvoices.io}},\n  institution  = {Data Science Nigeria},\n  keywords     = {speech recognition, multilingual datasets, African languages, low-resource ASR}\n}\n\n@article{emezue2025naijavoices,\n  title   = {The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages},\n  author  = {Emezue, Chris and Community, NaijaVoices and Awobade, Busayo and Owodunni, Abraham and Emezue, Handel and Emezue, Gloria Monica Tobechukwu and Emezue, Nefertiti Nneoma and Ogun, Sewade and Akinremi, Bunmi and Adelani, David Ifeoluwa and others},\n  journal = {arXiv preprint arXiv:2505.20564},\n  year    = {2025}\n}\n\n@misc{lynguallabs_yecs_2026,\n  title        = {{YECS}: A 120-Hour Community-Curated Yoruba-English Code-Switching Corpus},\n  author       = {{LyngualLabs}},\n  year         = {2026},\n  note         = {140 speakers; 16 semantic domains; word-level language tags},\n  howpublished = {\\url{https://lynguallabs.org/yecs}}\n}\n\n@article{waxal2026,\n  title   = {WAXAL: A Large-Scale Multilingual African Language Speech Corpus},\n  author  = {Anonymous},\n  journal = {arXiv preprint arXiv:2602.02734},\n  year    = {2026}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "4a24943b0539404c0befaa2f6a59322d39dabb05",
 "stated_evidence": "https://huggingface.co/datasets/Professor/yoruba-speech-data/blob/4a24943b0539404c0befaa2f6a59322d39dabb05/README.md",
 "file_evidence": "https://huggingface.co/datasets/Professor/yoruba-speech-data/tree/4a24943b0539404c0befaa2f6a59322d39dabb05",
 "card_nc": false
}