{
 "id": "wenet-e2e/wenetspeech",
 "owner": "wenet-e2e",
 "name": "wenetspeech",
 "downloads": 6975,
 "likes": 9,
 "last_modified": "2024-07-04T10:20:36.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [],
 "citation": "Please cite this paper if you find this work useful:\n\n```bibtext\n@inproceedings{zhang2022wenetspeech,\n  title={Wenetspeech: A 10000+ hours multi-domain mandarin corpus for speech recognition},\n  author={Zhang, Binbin and Lv, Hang and Guo, Pengcheng and Shao, Qijie and Yang, Chao and Xie, Lei and Xu, Xin and Bu, Hui and Chen, Xiaoyu and Zeng, Chenchen and others},\n  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},\n  pages={6182--6186},\n  year={2022},\n  organization={IEEE}\n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "5fe6045424583e9480cc6ca2a09df6932e3d51fd",
 "stated_evidence": "https://huggingface.co/datasets/wenet-e2e/wenetspeech/blob/5fe6045424583e9480cc6ca2a09df6932e3d51fd/README.md",
 "file_evidence": "https://huggingface.co/datasets/wenet-e2e/wenetspeech/tree/5fe6045424583e9480cc6ca2a09df6932e3d51fd",
 "card_nc": false
}