zhvng/open-musiclm
A PyTorch implementation of Google's MusicLM for generating music from text prompts.

This repository reproduces MusicLM, a state-of-the-art text-to-music generation model from Google Research. It replaces MuLan with CLAP for joint audio-text embedding, SoundStream with Meta’s Encodec for neural audio coding, and w2v-BERT with MERT for audio representation. The system uses transformer-based architectures with attention mechanisms to generate musical audio conditioned on text descriptions. Early audio samples are available demonstrating the model’s text-to-music generation capabilities.
Frequently asked
- What is zhvng/open-musiclm?
- A PyTorch implementation of Google's MusicLM for generating music from text prompts.
- Is open-musiclm open source?
- Yes — zhvng/open-musiclm is open source, released under the MIT license.
- What language is open-musiclm written in?
- zhvng/open-musiclm is primarily written in Python.
- How popular is open-musiclm?
- zhvng/open-musiclm has 560 stars on GitHub.
- Where can I find open-musiclm?
- zhvng/open-musiclm is on GitHub at https://github.com/zhvng/open-musiclm.