FAST-RIRThis is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.
Stars: ✭ 90 (+328.57%)
wenetProduction First and Production Ready End-to-End Speech Recognition Toolkit
Stars: ✭ 2,384 (+11252.38%)
genalogGenalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.
Stars: ✭ 234 (+1014.29%)
SegSwap(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Stars: ✭ 46 (+119.05%)
mix3dMix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)
Stars: ✭ 183 (+771.43%)
kaldi helpers🙊 A set of scripts to use in preparing a corpus for speech-to-text processing with the Kaldi Automatic Speech Recognition Library.
Stars: ✭ 13 (-38.1%)
mtss-ganMTSS-GAN: Multivariate Time Series Simulation with Generative Adversarial Networks (by @firmai)
Stars: ✭ 77 (+266.67%)
cramcram is a computational room acoustics module to simulate and explore various acoustic properties of a modeled space
Stars: ✭ 23 (+9.52%)
CAP augmentationCut and paste augmentation for object detection and instance segmentation
Stars: ✭ 93 (+342.86%)
FmixOfficial implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'
Stars: ✭ 252 (+1100%)
gretel-python-clientThe Gretel Python Client allows you to interact with the Gretel REST API.
Stars: ✭ 28 (+33.33%)
deep avsrA PyTorch implementation of the Deep Audio-Visual Speech Recognition paper.
Stars: ✭ 104 (+395.24%)
pygsoundImpulse response generation based on state-of-the-art geometric sound propagation engine.
Stars: ✭ 86 (+309.52%)
soxanWav2Vec for speech recognition, classification, and audio classification
Stars: ✭ 113 (+438.1%)
room-impulse-responsesA list of publicly available room impulse response datasets and scripts to download them.
Stars: ✭ 143 (+580.95%)
VisDA2020VisDA2020: 4th Visual Domain Adaptation Challenge in ECCV'20
Stars: ✭ 53 (+152.38%)
leopardOn-device speech-to-text engine powered by deep learning
Stars: ✭ 354 (+1585.71%)
SDMetricsMetrics to evaluate quality and efficacy of synthetic datasets.
Stars: ✭ 67 (+219.05%)
multi-task-defocus-deblurring-dual-pixel-nimatReference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single …
Stars: ✭ 29 (+38.1%)
sova-asrSOVA ASR (Automatic Speech Recognition)
Stars: ✭ 123 (+485.71%)
discolightdiscolight is a robust, flexible and infinitely hackable library for generating image augmentations ✨
Stars: ✭ 25 (+19.05%)
Torch AudiomentationsFast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
Stars: ✭ 164 (+680.95%)
NlpaugData augmentation for NLP
Stars: ✭ 2,761 (+13047.62%)
textaugmentTextAugment: Text Augmentation Library
Stars: ✭ 280 (+1233.33%)
Robotics-Object-Pose-EstimationA complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.
Stars: ✭ 153 (+628.57%)
synthThe Declarative Data Generator
Stars: ✭ 958 (+4461.9%)
game-feature-learningCode for paper "Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery", Ren et al., CVPR'18
Stars: ✭ 68 (+223.81%)
BadMedicineLibrary and CLI for randomly generating medical data like you might get out of an Electronic Health Records (EHR) system
Stars: ✭ 18 (-14.29%)
genstarGeneration of Synthetic Populations Library
Stars: ✭ 17 (-19.05%)
ImgaugImage augmentation for machine learning experiments.
Stars: ✭ 12,107 (+57552.38%)
deep utilsAn open-source toolkit which is full of handy functions, including the most used models and utilities for deep-learning practitioners!
Stars: ✭ 73 (+247.62%)
Three-Filters-to-NormalThree-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator (RAL+ICRA'21)
Stars: ✭ 41 (+95.24%)
smognSynthetic Minority Over-Sampling Technique for Regression
Stars: ✭ 238 (+1033.33%)
table-evaluatorEvaluate real and synthetic datasets with each other
Stars: ✭ 44 (+109.52%)
obviA Polymer 3+ webcomponent / button for doing speech recognition
Stars: ✭ 54 (+157.14%)
timber-ruby🌲 Great Ruby logging made easy.
Stars: ✭ 155 (+638.1%)
ImageMethodReverb.jlRoom Acoustics Impulse Response Generator using the Randomized Image Method (RIM)
Stars: ✭ 23 (+9.52%)
imgcropSimple image augmentation library focusing on random geometric cropping
Stars: ✭ 27 (+28.57%)
Clustering-DatasetsThis repository contains the collection of UCI (real-life) datasets and Synthetic (artificial) datasets (with cluster labels and MATLAB files) ready to use with clustering algorithms.
Stars: ✭ 189 (+800%)
demo vietasrVietnamese Speech Recognition
Stars: ✭ 22 (+4.76%)
zpySynthetic data for computer vision. An open source toolkit using Blender and Python.
Stars: ✭ 251 (+1095.24%)
Speech-RecognitionEnd-to-End Speech Recognition using Neural Networks.
Stars: ✭ 31 (+47.62%)
augraphyAugmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes
Stars: ✭ 49 (+133.33%)
VidaugEffective Video Augmentation Techniques for Training Convolutional Neural Networks
Stars: ✭ 178 (+747.62%)
DeepEchoSynthetic Data Generation for mixed-type, multivariate time series.
Stars: ✭ 44 (+109.52%)
Timber Ruby🌲 Great Ruby logging made easy.
Stars: ✭ 154 (+633.33%)
torch-pitch-shiftPitch-shift audio clips quickly with PyTorch (CUDA supported)! Additional utilities for searching efficient transformations are included.
Stars: ✭ 70 (+233.33%)
SDGymBenchmarking synthetic data generation methods.
Stars: ✭ 177 (+742.86%)
obman render[cvpr19] Code to generate images from the ObMan dataset, synthetic renderings of hands holding objects (or hands in isolation)
Stars: ✭ 61 (+190.48%)
uoaisCodes of paper "Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling", ICRA 2022
Stars: ✭ 77 (+266.67%)
2018-dlslUPC Deep Learning for Speech and Language 2018
Stars: ✭ 18 (-14.29%)