{
 "id": "kensho/spgispeech",
 "owner": "kensho",
 "name": "spgispeech",
 "downloads": 2459,
 "likes": 42,
 "last_modified": "2026-01-20T16:29:00.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "automatic-speech-recognition"
 ],
 "citation": "Please cite this paper:\n\n```bibtext\n@ARTICLE{2021arXiv210402014O,\n       author = {{O'Neill}, Patrick K. and {Lavrukhin}, Vitaly and {Majumdar}, \n       Somshubra and {Noroozi}, Vahid and {Zhang}, Yuekai and {Kuchaiev}, Oleksii and {Balam}, \n       Jagadeesh and {Dovzhenko}, Yuliya and {Freyberg}, Keenan and {Shulman}, Michael D. and {Ginsburg}, \n       Boris and {Watanabe}, Shinji and {Kucsko}, Georg},\n        title = \"{SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition}\",\n      journal = {arXiv e-prints},\n     keywords = {Computer Science - Computation and Language, Electrical Engineering and Systems Science - Audio and Speech Processing},\n         year = 2021,\n        month = apr,\n          eid = {arXiv:2104.02014},\n        pages = {arXiv:2104.02014},\narchivePrefix = {arXiv},\n       eprint = {2104.02014},\n primaryClass = {cs.CL},\n       adsurl = {https://ui.adsabs.harvard.edu/abs/2021arXiv210402014O},\n      adsnote = {Provided by the SAO/NASA Astrophysics Data System}\n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "14e69dd3b80e968282ca55d3eb2b39cc9db2b62e",
 "stated_evidence": "https://huggingface.co/datasets/kensho/spgispeech/blob/14e69dd3b80e968282ca55d3eb2b39cc9db2b62e/README.md",
 "file_evidence": "https://huggingface.co/datasets/kensho/spgispeech/tree/14e69dd3b80e968282ca55d3eb2b39cc9db2b62e",
 "card_nc": false
}