a43992899/MARBLE
State-of-the-art pretrained music models for training, evaluation, inference
This tool helps music researchers and data scientists apply cutting-edge AI models to audio data. It takes raw audio files and associated labels as input, and outputs trained models that can classify, tag, or understand various aspects of music. The primary users are researchers or engineers working on music information retrieval, audio signal processing, or computational musicology projects.
166 stars.
Use this if you need to experiment with and compare state-of-the-art pretrained music models for tasks like genre classification, instrument recognition, or emotion detection in music.
Not ideal if you are a musician or artist looking for a tool to create or modify music directly, or if you need a simple, ready-to-use application without deep technical configuration.
Stars
166
Forks
16
Language
Python
License
—
Category
Last pushed
Jan 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/a43992899/MARBLE"
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