End-to-End Audio Transformer PyTorch Lightning implementation

This repository contains a simple PyTorch Lightning implementation of the paper End-to-End Audio Transformer by Avi Gazneli, Gadi Zimerman, Tal Ridnik, Gilad Sharir, Asaf Noy.

Original code can be found at https://github.com/Alibaba-MIIL/AudioClassfication

Setup

See .devcontainer/README.md for instructions on how to setup the development environment.

Data

We use the ESC-50 dataset downloaded from Huggingface "ashraq/esc50" for testing.

Notebook

See notebooks/lightning.ipynb for a simple example of how to train the model with Lightning.