Mohamed Nabih's Projects
My profile repository
NeMo: a toolkit for conversational AI
Keras/Pytorch neural network size, operations and parameters counter
Audio processing by using pytorch 1D convolution network
Problem Agnostic Speech Encoder
Collection of EM algorithms for blind source separation of audio signals
PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models (Accepted to 2023 ACII)
Improving Perceptual Quality by Phone-Fortified Perceptual Loss for Speech Enhancement
Curated list of project-based tutorials
Yet another speech toolkit based on Kaldi and PyTorch
Deep Learning Zero to All - Pytorch
ASR with PyTorch
pytorch tutorial for beginners
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Count the MACs / FLOPs of your PyTorch model.
Speech commands recognition with PyTorch
PyTorch Tutorial for Deep Learning Researchers
Build your neural network easy and fast
PyTorch1.x tutorials, examples and some books I found ใไธๅฎๆๆดๆฐไธญใๆด็็PyTorch 1.x ๆๆฐ็ๆ็จใไพๅญๅไนฆ็ฑ
Course code for PyTorch for Deep Learning with Python Bootcamp
This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation supports dropout and batch normalization. An example for phoneme recognition using the standard TIMIT dataset is provided.
A PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"
SEGAN pytorch implementation https://arxiv.org/abs/1703.09452
Speech Enhancement Generative Adversarial Network in PyTorch
Self-supervised Speech Enhancement network
๐ฆ A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding