wesbz
Graduated: 🎓 Computer Science @ CentraleSupélec 🎓 Maths & Machine Learning @ ENS Paris-Saclay Previously interned @ ENS Paris 💻 & Facebook AI Research 💻
Paris' suburb
Pinned Repositories
Alba
A music sheet writer !
arrayfire
ArrayFire: a general purpose GPU library.
audioset_tagging_cnn
BanditAgents
Implementations of known algorithms for the bandit problem
chatflix-1
CS-188-Pacman-Practice
Practice for a course using Berkeley's CS-188 resources
denoiser
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.
Hotword-Detection
Project for Voice Recognition course.
RLAlgo
A few Reinforcement Learning algorithms studied in class
SoundStream
This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf
wesbz's Repositories
wesbz/SoundStream
This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf
wesbz/nn-basis
wesbz/arrayfire
ArrayFire: a general purpose GPU library.
wesbz/audioset_tagging_cnn
wesbz/denoiser
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.
wesbz/fast-style-transfer
TensorFlow CNN for fast style transfer ⚡🖥🎨🖼
wesbz/flashlight
A C++ standalone library for machine learning
wesbz/fourier-drawing
A small tool
wesbz/franken_route
wesbz/free-privacy-notice
Open source privacy notice design patterns.
wesbz/jaxnerf
wesbz/lingua
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
wesbz/MarikIshtar007
wesbz/matplotlib
matplotlib: plotting with Python
wesbz/multilingual_kws
Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
wesbz/MVA-DL
wesbz/pal
PAL: Predictive Analysis & Laws of Large Language Models
wesbz/PEC
Plateform Expo Complex
wesbz/poop-my-pdf
A script for watermarking PDFs with a text paragraph
wesbz/pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding
wesbz/pyannote-database
Common interface to multimedia databases
wesbz/pytorch3d-nerf
wesbz/RouLette
I built an OpenAI European Roulette (single 0) environment.
wesbz/sgan
A wrapper for stylegan2 with ada. You can train a model with just six lines of code.
wesbz/solidity
Solidity, the Smart Contract Programming Language
wesbz/svgpathtools
A collection of tools for manipulating and analyzing SVG Path objects and Bezier curves.
wesbz/torchaudio-augmentations
Audio transformations library for PyTorch
wesbz/vector-quantize-pytorch
Vector Quantization, in Pytorch
wesbz/wesbz
wesbz/wesbz.github.io
Personal site, blog, and portfolio.