Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music

ArXi:2605.14765v1 Announce Type: cross Persian music, with its unique tonalities, modal systems (Dastgah), and rhythmic structures, presents significant challenges for music generation models trained primarily on Western music. We address this gap by curating the first large-scale dataset of Persian songs, comprising over 900 hours high-quality audio samples across diverse sub-genres, including pop, traditional, and contemporary styles.