aRI0U

flash-attention

Fast and memory-efficient exact attention

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

lightning-hydra-template

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

ffcv

FFCV: Fast Forward Computer Vision (and other ML workloads!)

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

POT

POT : Python Optimal Transport

torchmetrics

Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.

nnAudio

Audio processing by using pytorch 1D convolution network

Conditional_Diffusion_MNIST

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

audioseal

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

mustango

Mustango: Toward Controllable Text-to-Music Generation

dora

Dora is an experiment management framework. It expresses grid searches as pure python files as part of your repo. It identifies experiments with a unique hash signature. Scale up to hundreds of experiments without losing your sanity.

DeepLearningMusicGeneration

State of the Art of Music Generation with Deep Learning and AI

VICRegL

VICRegL official code base

FFCV-SSL

FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.

WavCaps

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

python_audio_loading_benchmark

Benchmark popular audio i/o packages

ISMIR-2023-Papers

ISMIR 2023 Papers: A complete collection of influential and exciting research papers from the ISMIR 2023 conference.

splinecam

Exact method for visualizing partitions of a Deep Neural Network, CVPR 2023 Highlight

MARBLE-Benchmark

Music Audio Representation Benchmark for Universal Evaluation

clip-rocket

Code release for "Improved baselines for vision-language pre-training"

slurm-ray-cluster

wandb-offline-sync-hook

A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!

eval-audio-repr

EVAR ~ Evaluation package for Audio Representations

equivariant-self-supervision-tempo

Official implementation of "Equivariant Self-Supervision for Musical Tempo Estimation (ISMIR 2022)"

ispa

ISMIR2019

Supplementary material for the ISMIR 2019 paper entitled "Multi-Task Learning of Tempo and Beat: Learning One to Improve the Other"

crepe_notes

Post-processing for CREPE to turn f0 pitch estimates into discrete notes e.g. MIDI

multipitch_architectures

Pytorch project accompanying the paper "Towards Improved Multi-Pitch Estimation: Large Architectures and the Challenge of Evaluation", submitted to IEEE/ACM Transactions on Audio, Speech & Language Processing

audio-resampling-in-python

Comparison of Python audio resampling implementations