{
 "id": "OpenLLM-France/Luciole-Audio-Evaluation-Dataset",
 "owner": "OpenLLM-France",
 "name": "Luciole-Audio-Evaluation-Dataset",
 "downloads": 140,
 "likes": 5,
 "last_modified": "2026-09-23T09:16:47.000Z",
 "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;\nthe attribution-required ones 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- **AMI Meeting Corpus** (CC-BY-4.0) — [source](https://groups.inf.ed.ac.uk/ami/corpus/)\n- **FLEURS** (CC-BY-4.0) — [source](https://huggingface.co/datasets/google/fleurs)\n- **MTJ-Jamendo (via AIR-Bench)** (CC-BY-NC-SA-4.0 (metadata) (text), Mixed per-track CC (Jamendo) — authorization required (audio)) — [source](https://github.com/MTG/mtg-jamendo-dataset)\n- **MusicCaps** (CC-BY-SA-4.0 (text), Copyrighted (YouTube / music industry rights) (audio)) — [source](https://www.kaggle.com/datasets/googleai/musiccaps)\n- **SLUE-SQA-5 (SLUE phase-2)** (Apache-2.0 / CC-BY-SA-4.0) — [source](https://huggingface.co/datasets/asapp/slue-phase-2)\n- **SpokenWOZ (via AIR-Bench)** (CC-BY-NC-4.0) — [source](https://spokenwoz.github.io/)\n- **SUMM-RE** (CC-BY-SA-4.0) — [source](https://huggingface.co/datasets/linagora/SUMM-RE)\n- **Vigogne (French Alpaca)** (CC-BY-NC-4.0 (text), Synthesized by OpenLLM-France (Chatterbox TTS) (audio)) — [source](https://github.com/bofenghuang/vigogne)\n\nThese also require keeping their text license/attribution notice (Apache-2.0 / MIT / CDLA):\n- **aya_collection** (Apache-2.",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "452e01038d21ea9e6607fad6adc418cfbb8c5c7d",
 "stated_evidence": "https://huggingface.co/datasets/OpenLLM-France/Luciole-Audio-Evaluation-Dataset/blob/452e01038d21ea9e6607fad6adc418cfbb8c5c7d/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenLLM-France/Luciole-Audio-Evaluation-Dataset/tree/452e01038d21ea9e6607fad6adc418cfbb8c5c7d",
 "card_nc": false
}