It's Raw! Audio Generation with State-Space Models
Paper
• 2202.09729 • Published
A completely pretrained version of SaShiMi model on big band music. Two versions are available, in the spirit of the original article :
- Full 8 layers model.
- Ablated 2 layers model.
See github fork.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support