<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Neural-Networks on Noureddine RAMDI</title><link>https://ramdi.fr/tags/neural-networks/</link><description>Recent content in Neural-Networks on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/neural-networks/index.xml" rel="self" type="application/rss+xml"/><item><title>Parrot: a privacy-first offline AI text-to-speech desktop app with Rust and Bun</title><link>https://ramdi.fr/github-stars/parrot-a-privacy-first-offline-ai-text-to-speech-desktop-app-with-rust-and-bun/</link><pubDate>Sat, 23 May 2026 20:41:14 +0000</pubDate><guid>https://ramdi.fr/github-stars/parrot-a-privacy-first-offline-ai-text-to-speech-desktop-app-with-rust-and-bun/</guid><description>Parrot is a Rust and Bun-powered offline AI text-to-speech app using Kokoro-82M model, streaming audio playback before synthesis completes. Supports 54 voices, 9 languages, fully private and GPU-free.</description></item><item><title>Inside X's recommendation engine: multi-stage candidate sourcing and neural ranking</title><link>https://ramdi.fr/github-stars/inside-x-s-recommendation-engine-multi-stage-candidate-sourcing-and-neural-ranking/</link><pubDate>Tue, 05 May 2026 13:37:39 +0000</pubDate><guid>https://ramdi.fr/github-stars/inside-x-s-recommendation-engine-multi-stage-candidate-sourcing-and-neural-ranking/</guid><description>Explore the architecture behind X&amp;rsquo;s For You Timeline recommendation system, built on Scala, Rust, and advanced ML models. Understand candidate sourcing, neural ranking, and filtering pipelines.</description></item><item><title>Inside Tesseract OCR: from legacy character recognition to LSTM-based line recognition</title><link>https://ramdi.fr/github-stars/inside-tesseract-ocr-from-legacy-character-recognition-to-lstm-based-line-recognition/</link><pubDate>Sun, 26 Apr 2026 09:31:26 +0000</pubDate><guid>https://ramdi.fr/github-stars/inside-tesseract-ocr-from-legacy-character-recognition-to-lstm-based-line-recognition/</guid><description>Tesseract OCR evolved from a legacy character pattern engine to a modern LSTM-based line recognition system supporting 100+ languages and multiple output formats. Here&amp;rsquo;s a technical dive.</description></item></channel></rss>