.png)
3 hours ago
1
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:
HuggingFace Model:
Extreme Degradation Bench:
# Create a virtual environment
uv venv cleanup --python=3.10
source cleanup/bin/activate
uv pip install -r requirements.txt
Download the model checkpoint from HuggingFace and place it in the root directory.
wget https://huggingface.co/smulelabs/Smule-Renaissance-Small/resolve/main/smule-renaissance-small.pt
python main.py {path-to-input} -o {path-to-output} -c {path-to-checkpoint}
