Polymath

Polymath uses machine learning to convert any music library (e.g from Hard-Drive or YouTube) into a music production sample-library. The tool automatically separates songs into stems (beats, bass, etc.), quantizes them to the same tempo and beat-grid (e.g. 120bpm), analyzes musical structure (e.g. verse, chorus, etc.), key (e.g C4, E3, etc.) and other infos (timbre, loudness, etc.), and converts audio to midi. The result is a searchable sample library that streamlines the workflow for music producers, DJs, and ML audio developers.

Polymath can be used to combine elements from different songs to create new compositions. It enables users to grab a beat, a bassline, and horns from different tracks and integrate them into a DAW. Its search capability helps discover related tracks to build mixes or datasets for model training.

Polymath includes documented installation, requirements, and usage steps, and describes how to add music to the library, quantize, search for similar songs, and convert audio to MIDI.

Use cases

• Create a large, searchable music dataset for ML model training
• Assemble hour-long DJ sets by finding related tracks and matching tempo