TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/M2D2 AS+

M2D2 AS+

Reported on 9 benchmarks across 5 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Music4 results

  • Music Auto-TaggingonMagnaTagATune
    PR-AUC· 2025-03-28
    41.6
    SOTA
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Music Auto-TaggingonMagnaTagATune
    ROC AUC· 2025-03-28
    91.8
    SOTA
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Music ClassificationonVocalSet
    Accuracy· uses extra data· 2025-03-28
    92.7
    SOTA
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Music ClassificationonVocalSet
    Accuracy · uses extra data· 2025-03-28
    78.9
    SOTA
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104

Audio3 results

  • Audio ClassificationonESC-50
    Accuracy (5-fold)· uses extra data· 2025-03-28
    98.5
    best: 99.1 (OmniVec2)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Audio ClassificationonESC-50
    Top-1 Accuracy· uses extra data· 2025-03-28
    98.5
    best: 99.1 (OmniVec2)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Instrument RecognitiononNSynth
    Accuracy· 2025-03-28
    79.7
    best: 80.6 (M2D-CLAP)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104

Methodology2 results

  • ClassificationonESC-50
    Accuracy (5-fold)· uses extra data· 2025-03-28
    98.5
    best: 99.1 (OmniVec2)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • ClassificationonESC-50
    Top-1 Accuracy· uses extra data· 2025-03-28
    98.5
    best: 99.1 (OmniVec2)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104