brangerbriz/midi-glove

Create MIDI note vector embeddings using GloVe (Global Vectors for Word Representation)

28
/ 100
Experimental

This tool helps music researchers and computational musicians understand relationships between musical notes in monophonic MIDI tracks. It takes your raw monophonic MIDI files or leverages a large pre-trained dataset, then transforms individual notes into numerical 'embeddings' that capture their musical context. The output is a set of multi-dimensional vectors (like coordinates) for each note, allowing you to mathematically compare notes and find patterns. Musicians, musicologists, and AI researchers interested in algorithmic composition or music analysis would find this useful.

No commits in the last 6 months.

Use this if you want to analyze or generate music by understanding the contextual relationships between individual notes in monophonic MIDI data.

Not ideal if you need to analyze polyphonic music, rhythm, or timing, as it specifically focuses on monophonic note sequences without rhythm information.

algorithmic-composition music-analysis music-information-retrieval computational-musicology midi-processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

22

Forks

4

Language

Jupyter Notebook

License

Last pushed

Apr 26, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/brangerbriz/midi-glove"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.