-
HMT Leipzig
- Leipzig
- https://egorpol.github.io/
Stars
A python package for handling modern staff notation of music
Visualisation, analysis, and annotation of music audio recordings
Text-to-Music Generation with Rectified Flow Transformers
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"
⚡ A Fast, Extensible Progress Bar for Python and CLI
Generative models for conditional audio generation
Library for the control of sound synthesis in OM
Edirom / MerMEId
Forked from kb-dk/MerMEIdMetadata Editor and Repository for MEI Data
llama3 implementation one matrix multiplication at a time
AudioSpylt: A Python toolbox inspired by audiosculpt/om, designed for in-depth audio analysis, advanced processing, and interactive visualization.
A musical instrument audio dataset generated on-the-fly using FM synthesis.
Differentiable FM Synthesis of Musical Instrument Sounds
370 Four-part Chorales by J.S. Bach in the Humdrum file format.
Gertim Alberda's digital edition of the 1898 Breitkopf print "389 Choralgesänge", republished for music research
Interactive Data Visualization in the browser, from Python
alsa-scarlett-gui is a Gtk4 GUI for the ALSA controls presented by the Linux kernel Focusrite USB Drivers
From-scratch diffusion model implemented in PyTorch.
Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".
Learning audio concepts from natural language supervision