{
 "id": "Sanghyang00/omniasr-molge",
 "owner": "Sanghyang00",
 "name": "omniasr-molge",
 "downloads": 846,
 "likes": 0,
 "last_modified": "2026-08-04T03:05:14.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition"
 ],
 "citation": "% source corpus\n@article{omnilingual2025omnilingual,\n  title={Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages},\n  author={Omnilingual, ASR and Keren, Gil and Kozhevnikov, Artyom and Meng, Yen and Ropers, Christophe and Setzler, Matthew and Wang, Skyler and Adebara, Ife and Auli, Michael and Balioglu, Can and others},\n  journal={arXiv preprint arXiv:2511.09690},\n  year={2025}\n}\n\n% processing papers\n@article{lee2026ur,\n  title={UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction},\n  author={Lee, Sangmin and Ahn, Eekgyun and Choi, Woongjib and Kang, Hong-Goo},\n  journal={arXiv preprint arXiv:2606.11681},\n  year={2026}\n}\n\n@article{lee2026molge,\n  title={MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition},\n  author={Lee, Sangmin and Chung, Woojin and Choi, Woongjib and Kang, Hong-Goo},\n  journal={arXiv preprint arXiv:2607.24030},\n  year={2026}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "a1d576c65b28ace356b67e2054fc48318ba0d439",
 "stated_evidence": "https://huggingface.co/datasets/Sanghyang00/omniasr-molge/blob/a1d576c65b28ace356b67e2054fc48318ba0d439/README.md",
 "file_evidence": "https://huggingface.co/datasets/Sanghyang00/omniasr-molge/tree/a1d576c65b28ace356b67e2054fc48318ba0d439",
 "card_nc": false
}