dataset_registry.json 1.05 KB
[
  {
    "name": "FMA",
    "source_url": "https://github.com/mdeff/fma",
    "license": "Track-dependent / metadata CC BY 4.0; verify per subset",
    "commercial_use": "review_required",
    "notes": "Good first realistic MIR baseline"
  },
  {
    "name": "MTG-Jamendo",
    "source_url": "https://github.com/MTG/mtg-jamendo-dataset",
    "license": "Creative Commons source tracks; verify exact subset terms",
    "commercial_use": "review_required",
    "notes": "Good retrieval/tagging corpus with scripts"
  },
  {
    "name": "CCMusic",
    "source_url": "https://ccmusic-database.github.io/en/database/ccm.html",
    "license": "varies / application may be required",
    "commercial_use": "review_required",
    "notes": "Useful Chinese MIR source, needs permission review"
  },
  {
    "name": "ModelScope-music",
    "source_url": "https://modelscope.cn/search?page=1&search=music&type=dataset",
    "license": "varies by dataset",
    "commercial_use": "deny_until_whitelisted",
    "notes": "Discovery surface only until per-dataset review is complete"
  }
]