Stars
Personal internet radio: Agentic AI DJ
Training-Efficient Text-to-Music Generation with State-Space Modeling
MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation
The official project page for the ISMIR 2026 paper, "MPECHO: A MELODY AND PHONEME-AWARE GENERATIVE FRAMEWORK FOR CONTROLLABLE COVER SONG GENERATION"
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
高频大厂面试题+电子书+此仓库作为面试的一条龙服务，其中包含面试真题，简历模板，后端技术精髓，当然也有生活相关比如租房坑等，简直暖心的仓库
使用命令行界面（CLI）或 Python 包进行简单易用的人声分离，采用各种出色的模型（主要由 @Anjok07 作为 UVR 项目的一部分训练）
Additional material for the paper ADTOF: A large dataset of non-synthetic music for automatic drum transcription
收录最全、更新最快的技能Skills 商店，涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流等多个领域的 72 个精选技能包。所有技能已打包完成，可直接安装使用！ 该商店中自动抓取了 Github 上的所有的 Skills 项目，并按照分类、更新时间、Star 数量等标签进行整理。
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Variational version of Monotonic Groove Transformer
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
A python script for extracting loops from audio files.
[ICLR 2026] SmartDJ: declarative audio editing with audio langugae model.
有梗接歌檢索 — 給定一首華語歌，用兩階段（字面/語意檢索 + LLM 裁判）找出最有梗的下一首下一句，AI DJ 串燒的選歌/選 cue 層
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
Fill-in-your-own-data framework for YouTube / short-form video automation: CapCut JSON + ffmpeg tooling + an onboarding questionnaire. Ships with zero private data.
An automated music mashup creation system using AI-assisted music analysis. Research project under the supervision of Prof. Andrew Horner at HKUST
for automatic transition point estimation (cue-in and cue-out) in DJ mixing.
Generates mood based playlists using Spotify listening history
PyTorch implementation of the paper Learning Multi-Level Representations for Hierarchical Music Structure Analysis presented at ISMIR 2022.
Dataset of the BLE packets and sensor data gathered during ADE2016
Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative a…
MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenarios.
DEMON: Diffusion Engine for Musical Orchestrated Noise