LOFI is a Machine Learning supported lo-fi music generator. The original authors trained a VAE model in PyTorch to represent a Lo-Fi track as a vector of 100 features. A Lo-Fi track consists of chords, melodies, and other musical parameters. The web client uses Tone.js to make a dusty lo-fi track out of these parameters.
Click here for a pre-generated Lo-Fi playlist!
The main objectives of this fork are the following:
- Convert scripts in more readable Jupyter Notebook format
- Study the effect on the samples by changing architecture parameters
- Implement a simple
generateSample()
feature without relying on the client - Implement an infinite loop feature, as the popular live-stream of Lofi Girl