linzai1992

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

spleeter

Deezer source separation library including pretrained models.

leedl-tutorial

《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

TTS

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

few-shot-vid2vid

Pytorch implementation for few-shot photorealistic video-to-video translation.

speech-driven-animation

loop

A method to generate speech across multiple speakers

Parakeet

PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS, FastSpeech2/FastPitch, SpeedySpeech, WaveFlow and Parallel WaveGAN)

matting_human_datasets

人像matting数据集，包含34427张图像和对应的matting结果图。

ForwardTacotron

⏩ Generating speech in a single forward pass without any attention!

FloWaveNet

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

Neural-Voice-Cloning-With-Few-Samples

This repository has implementation for "Neural Voice Cloning With Few Samples"

matlab-dockerfile

Create a docker container that contains a MATLAB install

ClariNet

A Pytorch Implementation of ClariNet

multi-speaker-tacotron

VCTK multi-speaker tacotron for ICASSP 2020

Neural-Voice-Cloning-with-Few-Samples

Implementation of Neural Voice Cloning with Few Samples Research Paper by Baidu

GAN-TTS

A pytroch implementation of the GAN-TTS: HIGH FIDELITY SPEECH SYNTHESIS WITH ADVERSARIAL NETWORKS

spectrogramJS

spectrogram visualization in the browser

WaveRNN-Pytorch

Fatcord's Alternative WaveRNN (Faster training)

Audiovisual-Synthesis

Unsupervised Any-to-many Audiovisual Synthesis via Exemplar Autoencoders

yang_vocoder

magphase

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.

videoprocess

CN-Celeb, a large-scale Chinese celebrities dataset published by Center for Speech and Language Technology (CSLT) at Tsinghua University.

style-token_tacotron2

style token with tacotron2

Talking_Face_Generation

Talking Face Generation by Conditional Recurrent Adversarial Network

PiENet

Pitch estimation network (PiENet) for noise-robust neural F0 estimation of speech signals

FilterBanks_FastPythonImplementation

Filter Banks, Fast Python Implementation

snreval

Objective measures of speech quality SNR

ahoproc_tools

Tools for Ahocoder data processing and evaluation metrics

speech2vid