| conf | ||
| experiments/trained_model | ||
| dataset_loader.py | ||
| environment.yml | ||
| inference.py | ||
| inference.sh | ||
| README.md | ||
| requirements.txt | ||
| train.py | ||
| train.sh | ||
| trainer.py | ||
| unet.py | ||
A two-stage U-Net for high-fidelity denoising of historical recordings
Official repository of the paper:
citation here
Abstract
abstract here
Requirements
You will need at least python 3.7. See ´requirements.txt´ for the required package versions.
To install the environment through anaconda, follow the instructions:
conda env update -f environment.yml
conda activate historical_denoiser