Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

Problem Agnostic Speech Encoder

Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval

Open Source Computer Vision Library

processing and extracting of face and mouth image files out of the TCDTIMIT database

音视频文件格式解析

Talking Face Generation by Conditional Recurrent Adversarial Network

The proposed method in LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild

The state-of-art PyTorch implementation of the method described in the paper "LipNet: End-to-End Sentence-level Lipreading" (https://arxiv.org/abs/1611.01599)

DenseNet3D Model In "LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild", https://arxiv.org/abs/1810.06990

CVPR 2019

Out of time: automated lip sync in the wild

You Said That?: Synthesising Talking Faces from Audio

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)

Self-Attention Generative Adversarial Networks Implementation in PyTorch

Assessing Generative Models via Precision and Recall (official repository)

Image Processing, Speech Processing, Encoder Decoder, Research Paper implementation

[NeurIPS 2019] Face Reconstruction from Voice using Generative Adversarial Networks

The implementation of StyleGAN on PyTorch 1.0.1

PyTorch API for GluonCV Models

Compare GAN code.

Code release for paper "How good is my GAN?"

An empirical study on evaluation metrics of generative adversarial networks.

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Include some core functions and model to handle speech separation