Deep Learning

Official Pytorch+Lightning Implementation for NU-Wave

NU-Wave

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
Junhyeok Lee, Seungu Han @ MINDsLab Inc., SNU

Paper(arXiv): https://arxiv.org/abs/2104.02321 (Accepted to INTERSPEECH 2021)
Audio Samples: https://mindslab-ai.github.io/nuwave

Official Pytorch+Lightning Implementation for NU-Wave.

sampling

Requirements

Preprocessing

Before running our project, you need to download and preprocess dataset to .pt files

  1. Download VCTK dataset
  2. Remove speaker p280 and p315
  3. Modify path of downloaded dataset data:dir in hparameters.yaml
  4. run utils/wav2pt.py
$ python utils/wav2pt.py

Training

  1. Adjust hparameters.yaml, especially train section.
train:
  batch_size: 18 # Dependent on GPU memory size
  lr: 0.00003
  weight_decay: 0.00
  num_workers: 64 # Dependent on CPU cores
  gpus: 2 # number of GPUs
  opt_eps: 1e-9
  beta1: 0.5
  beta2: 0.999