MusicCaps

MusicTextsCC BY-SA 4.0Introduced 2023-01-26

MusicCaps is a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts. For each 10-second music clip, MusicCaps provides:

A free-text caption consisting of four sentences on average, describing the music and
A list of music aspects, describing genre, mood, tempo, singer voices, instrumentation, dissonances, rhythm, etc.

Source:MusicLM: Generating Music From Text

Benchmarks

Text-to-Music Generation/FAD Text-to-Music Generation/FD_openl3 Text-to-Music Generation/FD Text-to-Music Generation/KL_passt Text-to-Music Generation/IS Text-to-Music Generation/CLAP_LAION Text-to-Music Generation/CLAP_MS