kkoutini

PaSST

Efficient Training of Audio Transformers with Patchout

cpjku_dcase19

CP-JKU submission to DCASE 19, performant single-model CNN

cpjku_dcase20

CP-JKU submission to DCASE 20

passt_hear21

Inference code for PaSST, using the HEAR API.

cpjku_dcase21

CP-JKU submission to DCASE 2021

ba3l

Ba3l

oat-tao-tao-openid-auth

Integrating TAO with Openid log in

sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

occ

Objective C educational compiler

clone-full-webpage

clone a webpage with resources

kapre

kapre: Keras Audio Preprocessors

kkoutini.github.io

android-jaxb

Android doesn't support JAXB. Use this library to generate SimpleXML annotated classes from XML Schema. Works well with Android.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

dcase_benchmarks

dotfiles

My dotfiles

extension-tao-itemqti

extension to create QTI items for TAO

hf-fastup

Scripts to upload large datasets fast in parallel to huggingface hub

incense

Interactively retrieve data from sacred experiments.

omniboard

Web-based dashboard for Sacred

perceiver-pytorch

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

pytorch-lightning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate