Skip to content

A melody sequencer project, using Tone.js and magenta.js. First time working with ML and building a web application.

Notifications You must be signed in to change notification settings

nol-alb/ML-melody-sequencer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ML-melody-sequencer

A simple melody step sequencer using Tone.js and NexusUI infused with magenta musicVAE trained models.

Screenshot of the UI:

The basic functionality of this application is to allow a user to create a melody from the notes in the chord c#m7, using the step sequencer over a predefined drum loop.

Onto this I have then incorporated two machine learning models to further enhance the capabilites of this application. Once the user inputs their desired timing for a melody, the application will then proceed to create its own variations over an 8 measure loop. Furthermore a Groove Drums button is added, which when pressed will generate variations of the existing drum loop, to humanize and create a sense of randomness.

This was my first time working with java script and html to create an interactive web application.

Here is a link to try it out!! https://fluffy-smush-machine.glitch.me

About

A melody sequencer project, using Tone.js and magenta.js. First time working with ML and building a web application.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published