MelRoFormer Full

CoreML model for Schism audio separation framework.

Full Mel-Band RoFormer (~72M params) for high-quality vocal separation

Details

Property Value
Expert IDs melroformer-full
Tasks vocalSeparation
Quality high
Est. RTF 0.6
Peak Memory 850 MB

Usage

Install to your local Schism model store:

schism models install melroformer-full

Or manually place in ~/.schism/models/melroformer-full/v1.0.0/.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support