Wassim (Wes) Bouaziz
wesbz
AI Scientist in AI Security & Safety | PhD from Meta FAIR & École polytechnique.
Languages
Repos
45
Stars
421
Forks
61
Top Language
Python
Loading contributions...
Top Repositories
This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf
A music sheet writer !
PyTorch native post-training library
Solidity, the Smart Contract Programming Language
Personal site, blog, and portfolio.
Repositories
45This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf
No description provided.
PyTorch native post-training library
Solidity, the Smart Contract Programming Language
Personal site, blog, and portfolio.
No description provided.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
PAL: Predictive Analysis & Laws of Large Language Models
No description provided.
Audio transformations library for PyTorch
matplotlib: plotting with Python
A music sheet writer !
A wrapper for stylegan2 with ada. You can train a model with just six lines of code.
A script for watermarking PDFs with a text paragraph
Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
Vector Quantization, in Pytorch
No description provided.
No description provided.
I built an OpenAI European Roulette (single 0) environment.
Open source privacy notice design patterns.
A C++ standalone library for machine learning
TensorFlow CNN for fast style transfer ⚡🖥🎨🖼
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
A small tool
A collection of tools for manipulating and analyzing SVG Path objects and Bezier curves.
No description provided.
No description provided.
ArrayFire: a general purpose GPU library.
Plateform Expo Complex
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding