{
 "id": "kensho/SPGISpeech2.0",
 "owner": "kensho",
 "name": "SPGISpeech2.0",
 "downloads": 3056,
 "likes": 5,
 "last_modified": "2026-04-29T22:16:51.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "kensho-research",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "automatic-speech-recognition"
 ],
 "citation": "<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->\n\n**BibTeX:**\n\n@misc{grossman2025spgispeech20transcribedmultispeaker,\n      title={SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription}, \n      author={Raymond Grossman and Taejin Park and Kunal Dhawan and Andrew Titus and Sophia Zhi and Yulia Shchadilova and Weiqing Wang and Jagadeesh Balam and Boris Ginsburg},\n      year={2025},\n      eprint={2508.05554},\n      archivePrefix={arXiv},\n      primaryClass={cs.SD},\n      url={https://arxiv.org/abs/2508.05554}, \n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "f4ce91de393ca8693968d403ae618e3d54452b56",
 "stated_evidence": "https://huggingface.co/datasets/kensho/SPGISpeech2.0/blob/f4ce91de393ca8693968d403ae618e3d54452b56/README.md",
 "file_evidence": "https://huggingface.co/datasets/kensho/SPGISpeech2.0/blob/f4ce91de393ca8693968d403ae618e3d54452b56/LICENSE",
 "card_nc": false
}