Mohamed Nabih's repositories
CausalityCheck
Causality Check in Frame-online Speech Separation
Enhancing-Embeddings
This is the official implementation of our paper "ENHANCING PRE-TRAINED SPEECH EMBEDDINGS FOR SPEECH RECOGNITION IN NOISY CONDITIONS".
Algo-Python
All Algorithms implemented in Python
audio-and-speech-tech-2022
Audio and Speech Technologies Workshop 2022, code examples
audio-speech-denoising
About Implementation and training of a deep neural network for speech denoising tasks.
audiomentations
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
CleanUNet
Official PyTorch Implementation of CleanUNet (ICASSP 2022)
end2end-asr-pytorch
End-to-End Automatic Speech Recognition on PyTorch
evaluate
A library for easily evaluating machine learning models and datasets.
flops-counter.pytorch
Flops counter for convolutional networks in pytorch framework
flopth
A simple program to calculate the FLOPs of Pytorch models, multiple inputs supported, with cli tool and Python APIs.
fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
LibriMix
An open source dataset for source separation
mayavoz
Pytorch based speech enhancement toolkit.
pb_bss
Collection of EM algorithms for blind source separation of audio signals
pytorch-deep-learning
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
pytorch-OpCounter
Count the MACs / FLOPs of your PyTorch model.
Speech-Command-Classification
Speech command classification on Speech-Command v0.02 dataset using PyTorch and torchaudio. In this example, three models have been trained using the raw signal waveforms, MFCC features and MelSpectogram features.
torchstat
Model analyzer in PyTorch
transformer
PyTorch Implementation of "Attention Is All You Need"
TRUNet
unofficial PyTorch implementation of 《REAL-TIME DENOISING AND DEREVERBERATION WTIH TINY RECURRENT U-NET》
Wav2Keyword
Wav2Keyword is keyword spotting(KWS) based on Wav2Vec 2.0. This model shows state-of-the-art in Speech commands dataset V1 and V2.