✌️ Mohamed Anwar's Projects
This is a special repo where I can change the overview of my profile.
My blog!
This repository contains my attempt to use two famous speech recognition frameworks (Kaldi, CMU Sphinx4) for Arabic Language using the publicly-available dataset "Arabic Corpus of Isolated Words"
This is a diacritization model for Arabic language. This model was built/trained using the Tashkeela: the Arabic diacritization corpus on Kaggle
This is a model written in python as an autocorrecter
A self-supervised learning framework for audio-visual speech
This repo contains a crawler that I have created to extract the names from Behind the name website which has more than 20,000 names.
This is a simple PoC (proof-of-concept) model built to restore punctuation & capitalization from a given text. In other words, given a text with no punctuations and no capitalization, this model is able to restore the needed punctuations and capitalization to make the text human-readable.
This repo contains my solution to the Coursera course "Calculus One" created by Prof. Jim Fowler from The Ohio State University.
This repo contains my solution to the Coursera course "Calculus Two: Sequences and Series" created by Prof. Jim Fowler from The Ohio State University.
This is my PyTorch implementation of the "Very Deep Convolutional Neural Networks For Raw Waveforms" research paper published in 2016.
A python implementation of the "Comparing the Level of Code-Switching in Corpora" paper. This model is just an evaluator to evaluate the complexity score of a code-switched corpus.
My solution to Natural Language Processing Columbia Course by Michael Collins in 2015
This is PyTorch implementation of the "Convolutional Sequence to Sequence Learning" paper published by FacebookAI in 2017.
This is my solution to "cracking the coding interview" problems in Python
This repo contains my solution to the Stanford course "NLP with Deep Learning" under CS224n code. Here, you can find the solution for all classes starting form 2018
This repo contains the solution to the MCQ Corrector Kaggle Competition.
My solution to the Natural Language Processing course made by Dan Jurafsky, Chris Manning in Winter 2012.
This repo contains my solution to the Udacity course "Data Analysis with R"
This repo contains my solution to the Data Analyst Track for the "One Million Arab Coders" program by Udacity 2018.
This repo contains my solution to the 10-courses Coursera Specilaization called "Data Science Specialization"
This repo contains my solution to the Udacity course "Data Wrangling with MongoDB"
This repo contains my journey taking the "Deep Learning Nanodegree" with Udacity!!
This repo contains my solution to the 5-course Coursera Deep Learning Specialization created by prof. Andrew Ng and deeplearning.ai incorporation in 2017-2018
This repository contains my solution to the assignments of the "EECS 498-007 / 598-005 Deep Learning for Computer Vision" course made by Michigan University Fall 2020.
extra-collections (or extra for short) is a python3 package that provides a pythonic, intuitive, and easy implementation of the most common data structures used in software projects.
This is the repository where I document my journey during the "Front-end Web Developer" Nanodegree provided by Udacity in late 2020
This is the repository where I document my journey during the "Full Stack Web Developer" Nanodegree provided by Udacity in mid 2020
This repo contains a scrapper for the Gutenberg's project website which contains 56,019 books free to read and download. In this repo also, you can find text file containing all the book data until April 2018 containing only the 'id', 'title' and 'authors' for every book in the dataset.
This repo contains my solution to the Udacity course "Intro to Data Science".