Mohamed Nabih's Projects
A toolbox that provides hackable building blocks for generic 1D/2D/3D UNets, in PyTorch.
All Algorithms implemented in Python
š§āš« 59 Implementations/tutorials of deep learning papers with side-by-side notes š; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), š® reinforcement learning (ppo, dqn), capsnet, distillation, ... š§
Federated Learning for Automatic Speech Recognition
Audio and Speech Technologies Workshop 2022, code examples
About Implementation and training of a deep neural network for speech denoising tasks.
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Collection of advice for prospective and current PhD students
A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
Script to calculate SNR and SDR using python
Causality Check in Frame-online Speech Separation
Official PyTorch Implementation of CleanUNet (ICASSP 2022)
pytorch implementation of complex convolutional neural network
A PyTorch implementation of Conv-TasNet
covid_fake_news
CTC end -to-end ASR for timit and 863 corpus.
Cheat sheets for Numpy, Pandas, SQL, Scikit Learn
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 PyTorch implementation of DNN-based source separation.
[ICML2024] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
Intent Classification using the Fluent Speech Commands Dataset
End-to-End Automatic Speech Recognition on PyTorch
This is the official implementation of our paper "ENHANCING PRE-TRAINED SPEECH EMBEDDINGS FOR SPEECH RECOGNITION IN NOISY CONDITIONS".
A library for easily evaluating machine learning models and datasets.
A extension toolkit for Kaldi ASR tools with Pyhton