OpenMusic (QA-MDT)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Audio3 results

Text-to-Music GenerationonMusicCaps
IS· 2024-05-24
2.8
best: 3.32 (ETTA)
SOTA
Quality-aware Masked Diffusion Transformer for Enhanced Music Generation arXiv:2405.15863
Text-to-Music GenerationonMusicCaps
FAD· 2024-05-24
1.65
best: 13.4 (Riffusion)
Quality-aware Masked Diffusion Transformer for Enhanced Music Generation arXiv:2405.15863
Text-to-Music GenerationonMusicCaps
KL_passt· 2024-05-24
1.31
best: 1.87 (UniAudio)
Quality-aware Masked Diffusion Transformer for Enhanced Music Generation arXiv:2405.15863