Coder Social home page Coder Social logo

asigalov61 / mini-musical-neural-net Goto Github PK

View Code? Open in Web Editor NEW

This project forked from edtky/mini-musical-neural-net

0.0 1.0 0.0 213.26 MB

Explaining the breakdown of Open AI's music generation project

Jupyter Notebook 99.73% Python 0.27%

mini-musical-neural-net's Introduction

Mini Musical Neural Net

Here, we attempt to dissect Open AI Scholar Christine Payne's project on Musical Neural Net and further her work to complete some unfinished compositions by famous musicians.

Getting Started

These instructions will get you a copy of the project up and running on your local machine.

  1. Clone this Github repo into your local machine.

  2. You will need to have the following packages install: pytorch, music21, jupyter, numpy

  3. Open the iPython Notebooks and follow the tutorial inside.

Data to train model

Notewise text files of piano, jazz, and chamber (piano & violin) can be downloaded here:

Basic Model Pipeline

  1. midi files for training goes into midi-files

  2. encoder takes input midi files and converts them to text files into txt-files/notewise/note_range62/sample_freq12/

  3. word_model takes text files as input and outputs generated text files into txt-files/notewise/custom

  4. notewise-decoder.py takes text files and decodes them back to midi files into output-midi-files

Important Files / Folders

notewise_decoder.py
a script to decode any generated txt file into midi

word_model.py
our baseline 2-layer lstm model (for cpu)

notebooks/2018-11-14_model02-cuda.ipynb
latest version of our 2-layer lstm model (for gpu)
experimenting with hyperparameters

output-midi-files/notewise/custom/run01_2018-11-14/
contains samples of generated files during training

Poster for Project

alt text

Acknowledgement

  • Christine Payne, Open AI Scholar, for her amazing work!
  • DJ Gan Team @ Berkeley MEng

Contact

If you face any issues or have any questions, please contact me at [email protected]

mini-musical-neural-net's People

Contributors

edtky avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.