Chris Donahue

wavegan. WaveGAN: Learn to synthesize raw audio with generative adversarial networks

nesmdb. The NES Music Database: use machine learning to compose music for the Nintendo Entertainment System!

sheetsage. Transcribe music into lead sheets!

LakhNES. Generate 8-bit chiptunes with deep learning

ddc. Dance Dance Convolution dataset tools and models

ilm. Easily fine tune GPT-2 to fill in missing text

music-cocreation-tutorial. Start-to-finish tutorial for interactive music co-creation in PyTorch and Tensorflow.js

sdgan. Official implementation of "Semantically Decomposing the Latent Spaces of Generative Adversarial Networks"

ddc_onset. Music onset detector from Dance Dance Convolution packaged as a lightweight PyTorch module

opengl_spectrogram. using JUCE to create a 3D spectrogram drawn with OpenGL

neural-loops. Make musical loops in the browser using WaveGAN, GANSynth, and MusicVAE

midi2key_linux. Simple script to convert MIDI inputs to hotkeys on linux

piano-genie-research-demo. This is the old Piano Genie demo. For a shiny new one, go to http://piano-genie.glitch.me

fall23-phd-prospectives. Info for prospective PhD students for Chris Donahue's lab at CMU starting Fall 23.

piano-transcribe-batch. Uses Magenta's Onsets and Frames piano transcription model to transcribe a batch of solo piano recordings

sheetsage-data.

ject. JUCE extended convolution techniques GUI

gdrive-wget. Generate wget commands for Google Drive links!

wavegan_examples. Sound examples for WaveGAN

mlc-llm. Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

gpsynth. audio synthesis using genetic programming

chrisdonahue.github.io. Jupyter Notebook

magenta. Magenta: Music and Art Generation with Machine Intelligence

sheetsage-lbd. Sound examples for Sheet Sage at ISMIR 2021 late breaking demos https://archives.ismir.net/ismir2021/latebreaking/000049.pdf

librosa. Python library for audio and music analysis

web-llm. Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.

magenta-js. Magenta.js: Music and Art Generation with Machine Intelligence in the Browser

wowchemy-hugo-themes. HTML

align_midi. Code for MIDI-audio alignment

js_audio_examples. repository for open source JS/Web Audio API computer music tutorials

advoc_examples. HTML

gclef-cmu.github.io. Lab website

Piano. Multisampled Piano implementation using Salamander Grand Piano Sounds

audiveris. Latest generation of Audiveris OMR engine

anticipation. Anticipatory Autoregressive Models