Unofficial PyTorch implementation of "Adversarial Audio Synthesis"
MIT License
WaveGAN is a raw audio generation network.
You only need to modify a simple config.py file to train and sample the network and do more.
config.py
This implementation uses:
A pytorch implementation of Paper "Improved Training of Wasserstein GANs"
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Quasi-Periodic Parallel WaveGAN Pytorch implementation
ProGAN with Standard, WGAN, WGAN-GP, LSGAN, BEGAN, DRAGAN, Conditional GAN, InfoGAN, and Auxiliar...
Unofficial PyTorch implementation of "GAN-QP: A Novel GAN Framework without Gradient Vanishing an...
Source code for "Training Generative Adversarial Networks Via Turing Test".
generative adversarial networks
SEGAN pytorch implementation https://arxiv.org/abs/1703.09452