Scott H. Hawley

panotti. A multi-channel neural network audio classifier using Keras

ml-audio-start. Suggestions for those interested in developing audio applications of machine learning

audio-classifier-keras-cnn. Audio Classifier in Keras using Convolutional Neural Network

signaltrain. learning audio effects with neural networks

aeiou. (ML) audio engineering i/o utils

DLAIE. Materials for Hawley's Deep Learning & AI Ethics course

fad_pytorch. Frechet Audio Distance evaluation in PyTorch

audio-algebra. alchemy with embeddings

SHAART. SHAART is a Python-based audio analysis toolkit, for educational purposes

midi-player. Python launcher of animated MIDI player by @cifkao & @magenta

vibrary. Vibrary is a GUI client for a user-trainable neural network tool to help producers find audio files on their hard drives

vicregaddon. A lightweight and modular parallel PyTorch implementation of VICReg (intended for audio)

PolarPatternPlotter. iOS app for measuring sound directivity of loudspeakers and microphones

blog_fastpages. Scott H. Hawley's Blog

SoundFieldsForever. App Suite for Visualizing Sound in 3D

flocoder. A teaching and research repository for exploring generative latent flow matching

prefigure. Run configuration management utils: combines configparser, argparse, and wandb.API

devblog3. another dev blog attempt

fastproaudio. End-to-end audio deep learning with fastai

FaceOSC-iOS. Port to iOS of Christopher Baker's FaceOSC for Kyle McDonald's ofxFaceTracker, with output set to be compatible with Rebecca Fiebrink's Wekinator

NASH_time_align. Learning to do Time Alignment. Built within the fastproaudio repo, cf. https://drscotthawley.github.io/fastproaudio/time_align.html

oplas. Official repository for "Operational Latent Spaces"

espiownage. Ownage of ESPI image inference. (Pronounced like "espionage" but with a little "own" in the middle.)

blog. my new blog site

image-capture-opencv. Python utility for image capture, frame subtraction, (e.g. for ESPI)

botograder. An autograder for jupyter notebooks

talks. talks I've given

audio-diffusion. zach's audio-diffusion work. check various branches (not main!)

sample-generator. Tools to train a generative model on arbitrary audio samples

SPNet. Object detection for ESPI images of oscillating steelpan drums

music-interpolation. Mix between music tracks using machine learning

room-shape. 'Deep' neural network learns (boxy) room shape given mode frequencies, or vice versa

jukebox. Code for the paper "Jukebox: A Generative Model for Music"

fastai2_audio. Audio Module for fastai v2

flow-matching-flowers. An exercise in flow-matching modeling of the Oxford Flowers dataset

Mask_RCNN_SPNet. Modificaton of "Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow", outputs floats instead of class labels

all-in-one. All-In-One Music Structure Analyzer

blog_quarto. Quarto version of former fastpages blog

descript-audio-codec. Training and inference scripts for the Descript audio codec.

RAVE. Bastardized version of Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

torchopenl3. openl3 audio embedding for PyTorch

LoopGAN. StyleGAN2 + MelGAN Audio Loop Generation

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

M2UGen. This is the official repository for M2UGen

TTTT. Trying To Teach Transformers - dump/playground for code

audiotools. Object-oriented handling of audio data, with GPU-powered augmentations, and more.

mrspuff. A library for Deep Learning education. (deep learning <=> having a school at the bottom of the ocean)

midi-model. Midi event transformer for music generation

add-menu-popover-demo. Swift: Example of a popover window with a navigation controller and multiple pages for user selection