After reading the readme I'm not sure how this works. Will the "prompt" be the "raw audio" of the song? And the model returns lyrics, chords, beat, melody and the tabs?

I'm looking for something that I can sing to (a self composed song without music) and it would recommend guitar cords/tabs + melody to accompany myself. Any ideas?

A transformer-based hybrid multimodal model, various transformer models address different problems in the field of music information retrieval, these models generate corresponding information dependencies that mutually influence each other.

An AI-powered multimodal project focused on music. Get chords, beats, lyrics, melody, and tabs for any song.

Data sourced from YouTube, which may be helpful for singing or playing the guitar.