{
 "id": "williamhtan/cld-multi-dataset",
 "owner": "williamhtan",
 "name": "cld-multi-dataset",
 "downloads": 82,
 "likes": 0,
 "last_modified": "2026-06-02T08:34:54.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "audio-classification",
  "automatic-speech-recognition"
 ],
 "citation": "If you use this dataset, please cite the CLD paper (ICML 2026) and the underlying\ncorpora: Common Voice (Ardila et al., 2020), the National Speech Corpus (IMDA),\nLahaja (Sanket et al., 2024), and MUSAN (Snyder et al., 2015).",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "9fe140e8b60e785f52cced8c8310f248e05553c9",
 "stated_evidence": "https://huggingface.co/datasets/williamhtan/cld-multi-dataset/blob/9fe140e8b60e785f52cced8c8310f248e05553c9/README.md",
 "file_evidence": "https://huggingface.co/datasets/williamhtan/cld-multi-dataset/tree/9fe140e8b60e785f52cced8c8310f248e05553c9",
 "card_nc": false
}