Epistemic Noise

Articles

Tutorials with the working parts left in.

Longer technical pieces originally published on Medium and Towards Data Science — Alexa, production ML, chatbots, deployment.

Darija

How We Expanded DODa to 500K Darija Examples

Darija is inconvenient for NLP — two scripts, flexible spelling, heavy borrowing. DODa’s latest expansion turns that inconvenience into a controlled 500K-row training corpus.

Darija

Teaching TranslateGemma Moroccan Darija: What Worked, What Broke, and What 32.8 BLEU Actually Means

Fine-tuning TranslateGemma 4B for Arabic-script Darija and Arabizi, moving the run between GPU clouds late in training, and figuring out whether 32.82 BLEU was actually good.

Series

5 chapters · 31 October 2021 – 9 September 2022

Alexa Skills with Python

A hands-on path from first skill to APL, multilingual support, and monetization — written for builders who want the working parts left in.

  1. 1. An Introduction
  2. 2. How to Create Alexa Skills with Python
  3. 3. The visual dimension
  4. 4. Multilingual Support
  5. 5. Monetization
Open series →
TensorFlow

How to Get the TensorFlow Developer Certificate Using Free Colab

You do not have to live in PyCharm. Pass the TensorFlow Developer Certificate with Colab’s GPUs and a plugin that only needs the saved models.

Production

Deploy multiple Flask Applications using Nginx and Gunicorn

A step-by-step tutorial on how to deploy multiple Flask applications on a Linux server using Nginx and Gunicorn.

Production

Machine Learning in production: Keras, Flask, Docker and Heroku

Machine Learning in production: Keras, Flask, Docker and Heroku

Production

A guide to building WhatsApp chatbots using Dialogflow and Firebase

A step-by-step tutorial to create smart chatbots for your business and have them interact with your backend — Twilio, Flask, Dialogflow, Firebase.