MusicLM
The website provides examples of Music Language Models (MLMs) developed using the SeaNet framework. These MLMs can generate music compositions based on input prompts and can be trained on various music datasets. The examples showcase the capabilities of the SeaNet framework in generating diverse and high-quality music compositions.
MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Their experiments show that MusicLM outperforms previous systems in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts.
Categories:
Tags:
Ad
Similar to MusicLM