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

M2D2

Reported on 6 benchmarks across 4 tasks · 1 paper

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

Audio3 results

  • Emotion RecognitiononEmomusic
    EmoA· 2025-03-28
    76.7
    best: 77.4 (M2D-CLAP)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Emotion RecognitiononEmomusic
    EmoV· 2025-03-28
    59.3
    best: 61.9 (M2D-CLAP)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Audio ClassificationonAudioSet
    Test mAP· 2025-03-28
    0.49
    best: 0.558 (OmniVec2)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104

Music2 results

  • Music ClassificationonVocalSet
    Accuracy· uses extra data· 2025-03-28
    91.8
    best: 92.7 (M2D2 AS+)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104
  • Music ClassificationonVocalSet
    Accuracy · uses extra data· 2025-03-28
    77.4
    best: 78.9 (M2D2 AS+)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104

Methodology1 result

  • ClassificationonAudioSet
    Test mAP· 2025-03-28
    0.49
    best: 0.558 (OmniVec2)
    M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAParXiv:2503.22104