# Predicting music popularity using DNNs

This is a model fine-tuned for music popularity classification, created as part of DH-401: Digital Musicology class on EPFL

## Team

* Elisa (elisa.michelet@epfl.ch)
* Michał (michal.bien@epfl.ch)
* Noé (noe.durandard@epfl.ch)

## Milestone 3

Main notebook presenting out results is available [here](https://nbviewer.jupyter.org/github/Glorf/DH-401/blob/main/milestone3.ipynb)

Notebook describing the details of Wav2Vec2.0 pre-training and fine-tuning for the task is available [here](https://nbviewer.jupyter.org/github/Glorf/DH-401/blob/main/milestone3-wav2vec2.ipynb)

## Milestone 2

Exploratory data analysis notebook is available [here](https://nbviewer.jupyter.org/github/Glorf/DH-401/blob/main/milestone2.ipynb)

## Milestone 1

Refined project proposal is available [here](https://github.com/Glorf/DH-401/blob/main/milestone0.md)


## Milestone 0

Original project proposal is available in git history [here](https://github.com/Glorf/DH-401/blob/bb14813ff2bbbd9cdc6b6eecf34c9e3c160598eb/milestone0.md)