b8ba9c81e6
|
||
|---|---|---|
| .. | ||
| .ipynb_checkpoints | ||
| __pycache__ | ||
| data | ||
| figures | ||
| models | ||
| pickles | ||
| README.md | ||
| cfg.py | ||
| cleanup.ipynb | ||
| eda.py | ||
| model.ipynb | ||
| predict.ipynb | ||
| predictions.csv | ||
README.md
Audio Classification
This repository contains an audio classification task developed in Jupyter Notebooks from following Seth Adams' Deep Learning for Audio Classification series. In it we begin with a labeled dataset consisting of .wav files with audio from a variety of instruments. In our cleanup file, we read in the data and visualize Time Series, Fourier Transforms, Filter Bank Coeffecients, and MFCCs based on the data. We then create envelopes for each and save the data.