linzai1992

google-research

Google Research

avatarify-python

Avatars for Zoom, Skype and other video-conferencing apps.

first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

stylegan

StyleGAN - Official TensorFlow Implementation

pifuhd

High-Resolution 3D Human Digitization from A Single Image.

vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

espnet

End-to-End Speech Processing Toolkit

deep-voice-conversion

Deep neural networks for voice conversion (voice style transfer) in Tensorflow

essentia

C++ library for audio and music analysis, description and synthesis, including Python bindings

ParallelWaveGAN

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

Montreal-Forced-Aligner

Command line utility for forced alignment using Kaldi

TransformerTTS

🤖💬 Transformer TTS: Implementation of a non-autoregressive Transformer based neural network for text to speech.

athena

an open-source implementation of sequence-to-sequence based speech processing engine

speechmetrics

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

chinese_text_normalization

Chinese text normalization for speech processing

CaricatureFace

The source code for paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model".

Voice-Converter-CycleGAN

Voice Converter Using CycleGAN and Non-Parallel Data

nara_wpe

Different implementations of "Weighted Prediction Error" for speech dereverberation

LipSync

LipSync for Unity3D 根据语音生成口型动画 支持fmod

g2pm

A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset

durian-pytorch

Implementation of "Duration Informed Attention Network for Multimodal Synthesis" paper in PyTorch.

crank

A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder

libri_css

Libri-CSS: dataset and evaluation pipeline

athena

An automation platform with a plugin architecture that allows you to easily create and share services.

seq2annotation

基于 TensorFlow & PaddlePaddle 的通用序列标注算法库（目前包含 BiLSTM+CRF, Stacked-BiLSTM+CRF 和 IDCNN+CRF，更多算法正在持续添加中）实现中文分词（Tokenizer / segmentation）、词性标注（Part Of Speech, POS）和命名实体识别（Named Entity Recognition, NER）等序列标注任务。

GST_Tacotron

Implementation of Global Style Token Tacotron in TensorFlow2

WaveGlow

A tensorflow implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis

spleeter-as-a-service

API implementation of Song Source spleeting from Spleeter by Deezer

Tacotron-2

Tensorflow implementation of DeepMind's Tacotron-2 (without wavenet)

Animated_Avatar_LipSync