{
 "id": "OpenLLM-France/Luciole-Audio-Training-Dataset",
 "owner": "OpenLLM-France",
 "name": "Luciole-Audio-Training-Dataset",
 "downloads": 431,
 "likes": 6,
 "last_modified": "2026-10-29T13:04:14.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition",
  "translation",
  "question-answering",
  "audio-classification"
 ],
 "citation": "This dataset builds on the work of many others. Several sources are under **attribution\n(CC-BY*)** licenses and **require credit**. Please attribute every source dataset you use\n(the table above lists all of them with their license and origin); the attribution-required\nones are highlighted here:\n\nThe following datasets carry a **CC-BY / attribution** license on their text and/or audio — you **must credit** them (and cite their papers) when you use this dataset:\n- **ACSYNT** (CC-BY-SA-4.0) — [source](https://huggingface.co/datasets/datasets-CNRS/acsynt)\n- **AMI Meeting Corpus** (CC-BY-4.0) — [source](https://groups.inf.ed.ac.uk/ami/corpus/)\n- **Arabic Speech Corpus (Halabi)** (CC-BY-4.0) — [source](https://en.arabicspeechcorpus.com/)\n- **CFPB** (CC-BY-NC-SA-4.0) — [source](http://cfpp2000.univ-paris3.fr/cfpb.html)\n- **CFPP2000** (CC-BY-NC-SA-3.0) — [source](https://www.ortolang.fr/market/corpora/cfpp2000)\n- **CLAPI** (CC-BY-NC-SA-4.0) — [source](http://clapi.icar.cnrs.fr/)\n- **CLEAR** (CC-BY-3.0 (text), CC-BY-NC-4.0 (Good-Sounds / Zenodo) (audio)) — [source](https://ieee-dataport.org/open-access/clear-dataset-compositional-language-and-elementary-acoustic-reasoning)\n- **Clotho (via AudioMCQ)** (Tampere University NC (text), Mixed CC per-file (CC0 … CC-BY-NC-3.0; Freesound) (audio)) — [source](https://huggingface.co/datasets/inclusionAI/AudioMCQ)\n- **Clotho-AQA** (MIT (text), Mixed CC per-file (CC0 … CC-BY-NC-3.0; Freesound) (audio)) — [source](https://zenodo.org/records/647320",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "0d12383297b72b8a36dd1b685e488bc59c1d806f",
 "stated_evidence": "https://huggingface.co/datasets/OpenLLM-France/Luciole-Audio-Training-Dataset/blob/0d12383297b72b8a36dd1b685e488bc59c1d806f/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenLLM-France/Luciole-Audio-Training-Dataset/tree/0d12383297b72b8a36dd1b685e488bc59c1d806f",
 "card_nc": false
}