WaivOps JAZ-DRM Dataset For Music ML

The JAZ-DRM Dataset is an open collection of 1,675 jazz drum loops in WAV format with paired JSON label files. It was created using an algorithmic framework to generate audio from a custom database of MIDI patterns and multi-velocity drum kit samples. The dataset supports training and fine-tuning AI models to learn high-performance drum notations for prompt-driven generation and other supervised learning tasks in music applications such as text-to-audio, tempo detection, rhythm analysis, and sound design.