Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

A playbook for systematically maximizing the performance of deep learning models.

A PyTorch-based Speech Toolkit

Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

PFFDTD is an open-source FDTD simulator for 3D room acoustics

Measuring Disentanglement: A Review of Metrics

A PyTorch implementation of "Robust Universal Neural Vocoding"

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

A method to generate speech across multiple speakers