{
 "id": "amazon-agi/SIFT-50M",
 "owner": "amazon-agi",
 "name": "SIFT-50M",
 "downloads": 676,
 "likes": 39,
 "last_modified": "2025-08-21T17:05:06.000Z",
 "stated_licence": "cdla-sharing-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "audio-text-to-text",
  "audio-classification",
  "text-to-speech",
  "audio-to-audio"
 ],
 "citation": "@article{pandey2025sift,\n  title={SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning},\n  author={Pandey, Prabhat and Swaminathan, Rupak Vignesh and Girish, KV and Sen, Arunasish and Xie, Jian and Strimel, Grant P and Schwarz, Andreas},\n  journal={arXiv preprint arXiv:2504.09081},\n  year={2025}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "f50f079e732c3a4220242ac970b83280ae32f3c6",
 "stated_evidence": "https://huggingface.co/datasets/amazon-agi/SIFT-50M/blob/f50f079e732c3a4220242ac970b83280ae32f3c6/README.md",
 "file_evidence": "https://huggingface.co/datasets/amazon-agi/SIFT-50M/tree/f50f079e732c3a4220242ac970b83280ae32f3c6",
 "card_nc": false
}