A more efficient yolov5 with oneflow backend 🎉🎉🎉

哔哩下载姬downkyi，哔哩哔哩网站视频下载工具，支持批量下载，支持8K、HDR、杜比视界，提供工具箱（音视频提取、去水印等）。

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

Wechat Chat History Exporter 微信聊天记录导出备份程序

Python interface to the WebRTC Voice Activity Detector

This is the official implementation of the paper AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization.

Simple text to phones converter for multiple languages

Distribution Preserving X Vectors

Software presented in the article "Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation".

Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

In defence of metric learning for speaker recognition

Gaussian mixture models in PyTorch.

Text to Speech Synthesis based on controllable latent representation

Seeing Wake Words: Audio-visual Keyword Spotting

Extensible, parallel implementations of t-SNE

g2p: English Grapheme To Phoneme Conversion

A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

torch version of LPCNet

Audio LPC (linear prediction code) using mel spectorgram, compatible for LPCNet

WaveRNN Vocoder + TTS

Efficient neural speech synthesis

Official PyTorch implementation of Speaker Conditional WaveRNN

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

深度学习经典、新论文逐段精读