smulelabs/Smule-Renaissance-Small

Smule Renaissance Small

A 10.4M paramater generative audio model for restoring degraded vocals in any situation that runs 10.5x faster than real-time on iPhone 12's CPU. Outperforms all open source models in subjective quality; matches commericial models on singing voice restoration.

Technical Report:

Extreme Degradation Bench:

---

Getting Started

Setting up environment

# Create a virtual environment
uv venv cleanup --python=3.10
source cleanup/bin/activate
uv pip install -r requirements.txt

Running the model

python main.py {path-to-input} -o {path-to-output} -c {path-to-checkpoint}