Official implementation of YingMusic-SVC.

[TCSVT] ME-TST

一个基于 JavaScript 的网盘文件下载地址获取工具。基于【网盘直链下载助手】修改 ，支持 百度网盘 / 阿里云盘 / 中国移动云盘 / 天翼云盘 / 迅雷云盘 / 夸克网盘 / UC网盘 / 123云盘 八大网盘

北航硕博研究生毕业设计论文模板（Word）

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Pitch-shifting, time-stretching, and vocoding of speech with Controllable LPCNet (CLPCNet)

Curated list of groundbreaking music generation research.

PyTorch Implementation of TCSinger 2(ACL 2025): Customizable Multilingual Zero-shot Singing Voice Synthesis

Diffusion-based singing voice pitch correction

Learning the Beauty in Songs: Neural Singing Voice Beautifier; ACL 2022 (Main conference); Official code

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

Official implementation of Neural Audio Fingerprint (ICASSP 2021)

A library that provides an embeddable, persistent key-value store for fast storage.

C library for generating audio fingerprints used by AcoustID

MySQL入门教程（MySQL tutorial book）

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

Robust Speech Recognition via Large-Scale Weak Supervision

🔊 Text-Prompted Generative Audio Model

Deezer source separation library including pretrained models.

Official repository of the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization".

Visualizer for neural network, deep learning and machine learning models

A song aesthetic evaluation toolkit trained on SongEval.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

CUDA Library Samples

Repository-level Repair Agent Based on SWE-Bench—JoyCode Agent

Fast CUDA matrix multiplication from scratch

CUDA 算子手撕与面试指南

My learning notes for ML SYS.

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉