Okan Köpüklü's starred repositories
lazypredict
Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning
Resemblyzer
A python package to analyze and compare voices with deep learning
pyroomacoustics
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
Deep-Learning-In-Production
Build, train, deploy, scale and maintain deep learning models. Understand ML infrastructure and MLOps using hands-on examples.
torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
4D-Facial-Avatars
Dynamic Neural Radiance Fields for Monocular 4D Facial Avater Reconstruction
MaskGIT-pytorch
Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf)
VGG-Speaker-Recognition
Utterance-level Aggregation For Speaker Recognition In The Wild
Text-to-sound-Synthesis
The source code of our paper "Diffsound: discrete diffusion model for text-to-sound generation"
sudo_rm_rf
Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.
pyaec
simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link adaptive filters)、frequency domain adaptive filters(frequency domain adaptive filter、frequency domain kalman filter) for acoustic echo cancellation.
IRM-based-Speech-Enhancement-using-LSTM
Ideal Ratio Mask (IRM) Estimation based Speech Enhancement using LSTM
DNN-based-Speech-Enhancement-in-the-frequency-domain
DNN-based SE in the frequency domain using Pytorch. You can test some state-of-the-art networks using T-F masking or spectral mapping method.
octuplet-loss
Repo for our Paper: Octuplet Loss: Make Your Face Recognition Model Robust to Image Resolution
synthehicle
[WACVW 2023] A massive synthetic dataset for 3D multi-target multi-camera tracking and segmentation.
GaitGraph2
Official code for "Towards a Deeper Understanding of Skeleton-based Gait Recognition" (CVPRW'22)
Object-Detection-Confidence-Bias
Code for "The Box Size Confidence Bias Harms Your Object Detector" (https://arxiv.org/abs/2112.01901)
x-face-verification
Repo for our Paper: Explainable Model-Agnostic Similarity and Confidence in Face Verification
driver-gaze-yolov5
This is the repo for the work "Where and What: Driver Attention-based Object Detection".
german-corpus-aligned
Alignments from CTC segmentation on Librispeech and Spoken Wikipedia Corpus