WaivOps JAZ-DRM: Open Audio Resources for Machine Learning in Music

JAZ-DRM Dataset JAZ-DRM Dataset is an open audio collection of drum recordings in the style of classic and modern jazz music. It features 1,675 audio loops provided in uncompressed stereo WAV format, along with paired JSON files containing label data for supervised training of generative AI audio models. Overview The dataset was developed using an algorithmic framework to randomly generate audio loops from a customized database of MIDI patterns and multi-velocity drum kit samples. It is intended for training or fine-tuning AI models to learn high-performance drum notations using paired labels adaptable for prompt-driven generation and other supervised learning tasks. Its primary purpose is to provide accessible content for machine learning applications in music. Potential use cases include text-to-audio, prompt engineering, feature extraction, tempo detection, audio classification, rhythm analysis, music information retrieval (MIR), sound design and signal processing. Specifications 1675 audio loops (approximately 4.9 hours) 16-bit WAV format Tempo range: 130-220 BPM Paired label data (WAV + JSON) Variational drum kit and patterns Subgenre styles (bebop, swing, ballad, modern, free jazz) A key map JSON file is provided for referencing and converting MIDI note numbers to text labels. You can update the text labels to suit your preferences. License This dataset was compiled by WaivOps, a crowdsourced music project managed by Patchbanks. All recordings have been sourced from verified composers and providers for copyright clearance. The JAZ-DRM Dataset is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). Additional Info For audio examples or more information about this dataset, please refer to the GitHub repository.JAZ-DRM 数据集 JAZ-DRM 数据集是一套面向经典与现代爵士乐风格的开源鼓乐录音音频合集。其收录1675条未压缩立体声WAV格式的音频循环片段，以及配套的标签JSON文件，可用于生成式AI音频模型的监督训练。 概述 本数据集基于算法框架开发，从定制化的MIDI节奏型数据库与多力度鼓组采样库中随机生成音频循环片段。其核心目标是支持AI模型的训练或微调，使模型能够借助适配提示词生成与其他监督学习任务的配对标签，掌握高质量鼓乐记谱技法。 本数据集的主要用途是为音乐领域的机器学习应用提供可及性内容。潜在应用场景涵盖文本转音频、提示词工程、特征提取、速度检测、音频分类、节奏分析、音乐信息检索（Music Information Retrieval, MIR）、声音设计与信号处理。 规格参数 1. 1675条音频循环片段，总时长约4.9小时 2. 16位WAV格式 3. 速度范围：130-220 BPM（每分钟节拍数） 4. 配对标签数据（WAV+JSON格式） 5. 多样化鼓组与节奏型 6. 涵盖爵士乐子流派风格：比波普（bebop）、摇摆乐（swing）、抒情爵士（ballad）、现代爵士、自由爵士（free jazz） 本数据集附带MIDI键位映射JSON文件，可用于将MIDI音符编号转换为文本标签，用户可根据自身需求自定义更新标签内容。 许可协议 本数据集由WaivOps汇编完成，该项目是由Patchbanks管理的众包音乐计划。所有录音素材均来自完成版权合规认证的作曲者与提供者。 JAZ-DRM 数据集采用知识共享署名4.0国际许可协议（CC BY 4.0）进行授权。 补充信息 如需获取音频示例或了解该数据集的更多详情，请访问其GitHub仓库。