---
tags:
- musicgen
license: cc-by-nc-4.0
---

Text-to-music model with optional melody conditioning. 1.5B params LM trained on top of a 32 kHz Encodec model. See [github.com/facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft) for more details.
The model is trained on MMI (Meta Music Initiative) + Shutterstock + Pond5.