Top 35 wavenet open source projects

PyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]

Time series prediction using dilated causal convolutional neural nets (temporal CNN)

A neural network for end-to-end music source separation

Seq2Seq, Bert, Transformer, WaveNet for time series prediction.

DeepMind's Tacotron-2 Tensorflow implementation

WaveNet vocoder

Speedy Wavenet generation using dynamic programming ⚡

GANs for time series generation in pytorch

Machine learning, in numpy

parallel wavenet based on nsynth

Speech Enhancement using Bayesian WaveNet

A Chainer implementation of VQ-VAE.

Wavenet and its applications with Tensorflow

WaveNet implementation with chainer

pytorch tacotron2 https://arxiv.org/pdf/1712.05884.pdf

TensorFlow implementation of VQ-VAE with WaveNet decoder, based on https://arxiv.org/abs/1711.00937 and https://arxiv.org/abs/1901.08810

An end-to-end speech recognition system with Wavenet. Built using C++ and python.

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN) with Pytorch

A neural network for end-to-end speech denoising

A Pytorch implementation of "FloWaveNet: A Generative Flow for Raw Audio"

Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"

A collection of time series prediction methods: rnn, seq2seq, cnn, wavenet, transformer, unet, n-beats, gan, kalman-filter

A Pytorch Implementation of ClariNet

WaveNet-Vocoder implementation with pytorch.

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)

A Chainer implementation of Fast WaveNet(mel-spectrogram vocoder).

A Chainer implementation of ClariNet.

PyTorch implementation of NVIDIA WaveGlow with constant memory cost.

Quasi-Periodic Parallel WaveGAN Pytorch implementation

Source code for "Transferring the Style of Homophonic Music Using Recurrent Neural Networks and Autoregressive Model"

Audio source separation (mixture to vocal) using the Wavenet

Generating birdsong with WaveNet

Basic wavenet and fftnet vocoder model.