Official Pytorch Implementation for "DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion" (AAAI 2024)
I have trained a model for over 200 epochs with a batch size of 64, using the LibriTTS-100 and 360 datasets.
From my experience with training diffusion-based VC models, I have observed that sufficient training is necessary, and the LR, depending on the batch size, also affects the convergence of the training.
Thank you, it performs well. I was looking at the loss printed for each epoch. However, results after performing inference with a saved checkpoint looks good.
I have trained a model for over 200 epochs with a batch size of 64, using the LibriTTS-100 and 360 datasets. From my experience with training diffusion-based VC models, I have observed that sufficient training is necessary, and the LR, depending on the batch size, also affects the convergence of the training.