Build a Django Rest API to serve an end-to-end speech synthesizer and deploy a production-ready version leveraging docker, Gunicorn and Nginx.

Photo by Kelly Sikkema on Unsplash

The recent improvements in the field of speech synthesis have lead to many innovative technologies, offering a wide range of useful applications like automatic speech recognition, natural speech synthesis, voice cloning, digital dictation, and so forth.

Deep learning has played an immensely important role in improving already existent speech synthesis approaches by replacing the entire pipeline process with neural networks trained on data alone.

Following that perspective, Tacontron2 has been a game-changer, achieving a mean opinion score MOS of 4.53, almost comparable to professionally recorded speech. Yet, its architecture is quite intuitive, formerly based on a recurrent sequence-to-sequence network that…


Build a Django API that performs background customization using semantic segmentation

Original Photo by Sole D’Alessandro G. on Unsplash

Introduction

Image segmentation has been a hot topic for a while now. Various uses cases involving segmentation had emerged in a bunch of different areas, machine vision, medical imaging, object detection, recognition tasks, traffic control systems, video surveillance and, a lot more. The intuition behind these intelligent systems is to capture the diverse components that form the image and therefore, teach computer vision models to grasp more insight and a better understanding of the scene and the context.


Overview of some image processing features — leveraging OpenCV-4.2.0 with Python

Original Photo by Matteo Vistocco on Unsplash

Image Processing is a field of knowledge that falls in Computer Vision. The premises of machine learning were first laid down by computer vision theory, applying a whole set of techniques to process and analyze imagery data to extract valuable information that computers and machines may use for a wide range of applications, such as:

  • Stitching: Turning overlapping photos into a seamless panorama
  • Morphing: Changing or merging through a smooth transition different pictures to create a new one
  • 3D Modeling: Converting 2D snapshots into a 3D composition
  • Face detection: Identifying human faces in digital images
  • Visual Authentication: Automatically logging your…


Complete guide to install OpenCV-4.2.0 in Windows 10

This post will guide you through all the steps for installing and configuring OpenCV-4.2.0 in Windows 10 (64-bit) for python use inside the Anaconda environment.

  • OpenCV with Anaconda, for Python 3.6.0+ development

I will focus here on OpenCV for python 3.6.0+, my previous post for VC++ integration can be found here.

Note: To follow along with the tutorial, I will assume that you already have Anaconda and Python 3.6.0 installed. If not, please feel free to install these tools before continuing to read further.

OpenCV-4.2.0 for Python

The steps for installing OpenCV through Anaconda are pretty easy and straight forward. …


Complete guide to install OpenCV-4.2.0 in Windows 10

This post will guide you through all the steps for installing and configuring OpenCV-4.2.0 in Windows 10 (64-bit) within 2 different environments:

  • OpenCV with Visual Studio 2019, for C++ development
  • OpenCV with Anaconda, for Python 3.6.0+ development

I will focus here on OpenCV for Visual Studio with C++, the other tutorial part for python and Anaconda can be found here.

Note: To follow along with the tutorial, I will assume that you already have Visual Studio 2019 installed. If not, please feel free to install these tools before continuing to read further.

OpenCV-4.2.0 for Visual Studio 2019

All the required steps for setting up OpenCV…


Giving a simplified understanding of the main components of a neural network.

Photo by Zachary Claret-Scott on Unsplash

I’ve been working in many machine learning projects involving neural network models built for different tasks in various contexts. But I always find myself working with high-level frameworks and tools that mostly hide the real structure of the models being used. Mainly due to the variety of existing libraries and frameworks helping developers around the world to quickly start with machine learning code, encouraging them to build endpoint applications that use intelligent models for the purpose of countless tasks, without necessarily helping them to understand what is really happening behind the scenes.

Unfortunately, acting in that way, people fail to…

Aymane Hachcham

Data Scientist at Spotbills | Machine Learning enthusiast. Contact me: hachcham.ayman@gmail.com

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store