Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"
Thanks for publishing the train code.
I saw the code,
"from data_loader import AudioDataset, MelSpectrogramFixed"
but it looks like I can't import it because I don't have data_loader.py.
Thank you.
Thanks for publishing the train code. I saw the code, "from data_loader import AudioDataset, MelSpectrogramFixed" but it looks like I can't import it because I don't have data_loader.py. Thank you.