Fast Timing-Conditioned Latent Audio Diffusion

Benchmark Model Rank Results
audio-generation-on-audiocapsStable Audio#6FD_openl3: 103.66KL_passt: 2.89CLAP_LAION: 0.41
text-to-music-generation-on-musiccapsStable Audio#17FD_openl3: 108.69KL_passt: 0.80