PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

Speedy Wavenet generation using dynamic programming ⚡

Pytorch library for fast transformer implementations

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

Python audio and music signal processing library

This is now the official location of the Merlin project.

Question answering dataset featured in "Teaching Machines to Read and Comprehend

Differentiable Vector Graphics Rasterization

NumPy interface with mixed backend execution

Keras WaveNet implementation

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

Chainer implementation of Deep Convolutional Generative Adversarial Network

A collection of links and notes on forced alignment tools

kapre: Keras Audio Preprocessors

Implementation of the Wave-U-Net for audio source separation

Generating faces with deconvolution networks

A method to generate speech across multiple speakers

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

Speech Enhancement Generative Adversarial Network in TensorFlow

My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).

Multilayer LSTM and Mixture Density Network for modelling path-level SVG Vector Graphics data in TensorFlow

GRUV is a Python project for algorithmic music generation.

Neural Style Transfer For Chinese Characters

A Generative Flow for Text-to-Speech via Monotonic Alignment Search