migperfer
Follow
Lists (9)
Starred repositories
29
stars
written in Jupyter Notebook
Clear filter
A multi-voice TTS system trained with an emphasis on quality
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
An adversarial example library for constructing attacks, building defenses, and benchmarking both
A scikit-learn compatible neural network library that wraps PyTorch
Materials for the Hugging Face Diffusion Models Course
Handout for the tutorial "Creating publication-quality figures with matplotlib"
The official code repository for examples in the O'Reilly book 'Generative Deep Learning'
Tools to train a generative model on arbitrary audio samples
Utility functions for handling MIDI data in a nice/intuitive way.
Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.
DiffusionFastForward: a free course and experimental framework for diffusion-based generative models
Steerable discovery of neural audio effects
PyTorch wrappers for using your model in audacity!
Inference algorithms for models based on Luce's choice axiom
The Harmonix Set: Beats, Downbeats, and Structural Annotations for Pop Music
The Song Describer dataset is an evaluation dataset made of ~1.1k captions for 706 permissively licensed music recordings.
Start-to-finish tutorial for interactive music co-creation in PyTorch and Tensorflow.js
Scales, Chords, and Cadences: Practical Music Theory for MIR Researchers
[ICLR 2023] "Dilated convolution with learnable spacings" Ismail Khalfaoui Hassani, Thomas Pellegrini and Timothée Masquelier
4 Hour cuSignal Tutorial - ICASSP 2021 Notebooks
MuChoMusic is a benchmark for evaluating music understanding in multimodal audio-language models.
cochleagram generation code in pytorch
Repo of my master thesis at Pompeu Fabra University: "Towards album artwork generation based on audio". We analyze VAEs and GANs to condition image generation with audio.
pyAudGrav allows a user to algorithmically edit and rearrange audio clips in time and space using Newtons' universal law gravity. Gravity, in this case, is a metaphor used to describe the relations…