Generative models for conditional audio generation

An Audio Language model for Audio Tasks

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

Official Jax Implementation of MaskGIT

Open reproduction of MUSE for fast text2image generation.

music generation with masked transformers!

Unofficial PyTorch implementation of Discrete Denoising Diffusion Probabilistic Model(D3PM)

A curated list of awesome self-supervised methods

Algorithm and data structure articles for https://cp-algorithms.com (based on http://e-maxx.ru)

This reporsitory contains metadata of WavCaps dataset and codes for downstream tasks.

A feature-rich command-line audio/video downloader

Development repository for the Triton language and compiler

Evaluate EfficientAT models on the Holistic Evaluation of Audio Representations Benchmark.

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

Train ImageNet *fast* in 500 lines of code with FFCV

Objective C educational compiler

This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles et al., 2022).

Python bindings for minimp3

Inference code for PaSST, using the HEAR API.

Pytorch domain adaptation package

Efficient Training of Audio Transformers with Patchout

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

A beautiful, simple, clean, and responsive Jekyll theme for academics

CP-JKU submission to DCASE 2021

A curated list of neural network pruning resources.

Web-based dashboard for Sacred