| Diff-SVC is a project for singing/speech conversion based on diffusion models. Inference/inference: View ./inference.ipynb Preprocessing/preprocessing: export PYTHONPATH=.CUDA_VISIBLE_DEVICES=0 python preprocessing/binarize.py –config training/config.yaml Training/training: CUDA_VISIBLE_DEVICES=0 python run.py –config training/config.yaml –exp_name [your project name] –reset For the detailed training process and various parameter introductions, please refer to the inference and training instructions… |
#Singingvoice #conversion #DiffSVC