jryban/frechet-music-distance
A library for computing Frechet Music Distance.
This tool helps music researchers and developers evaluate the quality of music generated by AI models. It takes two collections of symbolic music files (like MIDI or ABC notation) – one representing a reference dataset and the other the AI-generated music – and calculates a Frechet Music Distance score. This score tells you how similar or different the generated music is compared to the reference, helping you understand how well your AI model is performing.
No commits in the last 6 months. Available on PyPI.
Use this if you are a researcher or developer working with generative music AI and need a robust, quantitative metric to compare your model's output against real or desired music datasets.
Not ideal if you need to evaluate music based on subjective human perception or if you are not working with symbolic music data (like raw audio).
Stars
28
Forks
4
Language
Python
License
MIT
Category
Last pushed
Feb 04, 2025
Commits (30d)
0
Dependencies
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jryban/frechet-music-distance"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Natooz/MidiTok
MIDI / symbolic music tokenizers for Deep Learning models 🎶
salu133445/muspy
A toolkit for symbolic music generation
jacbz/Lofi
ML-supported lo-fi music generator
jisungk/deepjazz
Deep learning driven jazz generation using Keras & Theano!
mdeff/fma
FMA: A Dataset For Music Analysis