---
title: "Bright Etornam Sunu (@iamEtornam) | Hashnode"
description: "Flutter & Dart GDE || Mobile & Backend Engineer || Technical writer || Community builder. Read the latest articles by Bright Etornam Sunu on Hashnode."
url: "https://hashnode.com/@iamEtornam"
---

@iamEtornam

# Bright Etornam Sunu

@iamEtornam · Accra, Ghana · Joined February 2019

Flutter & Dart GDE || Mobile & Backend Engineer || Technical writer || Community builder

[Website](https://etornam.dev/)

### [Beyond the Basics: Offline Models, Custom Signs, and Production Scaling (Part 4)](https://iametornam.hashnode.dev/beyond-the-basics-offline-models-custom-signs-and-production-scaling-part-4?utm_source=hashnode&utm_medium=feed)

This article explores the real-time inference pipeline of an ASL-to-voice project, detailing how sliding windows, CTC decoding, LLM-based translation, and multi-threaded text-to-speech work together to create a fluid user experience. It highlights the technical strategies used to overcome latency, ensuring the system remains responsive while translating sign language into natural, spoken English.

4 min read · [iametornam.hashnode.dev](https://iametornam.hashnode.dev/beyond-the-basics-offline-models-custom-signs-and-production-scaling-part-4?utm_source=hashnode&utm_medium=feed)

[May 16](https://hashnode.com/posts/beyond-the-basics-offline-models-custom-signs-and-production-scaling-part-4/6a08ac8d74b18db6860a680f)

### [Bringing it to Life: The Real-Time Inference Engine (Part 3)](https://iametornam.hashnode.dev/bringing-it-to-life-the-real-time-inference-engine-part-3?utm_source=hashnode&utm_medium=feed)

This article explores the real-time inference pipeline of an ASL-to-voice project, detailing how sliding windows, CTC decoding, LLM-based translation, and multi-threaded text-to-speech work together to create a fluid user experience. It highlights the technical strategies used to overcome latency, ensuring the system remains responsive while translating sign language into natural, spoken English.

5 min read · [iametornam.hashnode.dev](https://iametornam.hashnode.dev/bringing-it-to-life-the-real-time-inference-engine-part-3?utm_source=hashnode&utm_medium=feed)

[Apr 24](https://hashnode.com/posts/bringing-it-to-life-the-real-time-inference-engine-part-3/69ebcbdfb463d4844c4786f6)

### [From Pixels to Predictions: Data Pipelines and Training the Sequence Model (Part 2)](https://iametornam.hashnode.dev/from-pixels-to-predictions-data-pipelines-and-training-the-sequence-model-part-2?utm_source=hashnode&utm_medium=feed)

This article explores the data pipeline for a real-time ASL-to-voice system, detailing how to extract normalized skeleton keypoints using MediaPipe and train a Transformer-based sequence model to interpret sign language.

5 min read · [iametornam.hashnode.dev](https://iametornam.hashnode.dev/from-pixels-to-predictions-data-pipelines-and-training-the-sequence-model-part-2?utm_source=hashnode&utm_medium=feed)

[Apr 17](https://hashnode.com/posts/from-pixels-to-predictions-data-pipelines-and-training-the-sequence-model-part-2/69e2c137fd22b8ad628a5dda)

### [Bridging the Silence: Building a Real-Time Sign Language Translator (Part 1)](https://iametornam.hashnode.dev/bridging-the-silence-building-a-real-time-sign-language-translator-part-1?utm_source=hashnode&utm_medium=feed)

The "asl-to-voice" project introduces a five-stage, real-time pipeline that utilizes computer vision and transformer-based machine learning to ...

4 min read · [iametornam.hashnode.dev](https://iametornam.hashnode.dev/bridging-the-silence-building-a-real-time-sign-language-translator-part-1?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/bridging-the-silence-building-a-real-time-sign-language-translator-part-1/69d8e6e5c8e5007ddb91095b) [Apr 10](https://hashnode.com/posts/bridging-the-silence-building-a-real-time-sign-language-translator-part-1/69d8e6e5c8e5007ddb91095b)

### [Prompt-Driven Development: The Next Evolution in Software Engineering](https://iametornam.hashnode.dev/prompt-driven-development-the-next-evolution-in-software-engineering?utm_source=hashnode&utm_medium=feed)

In this new paradigm, natural language prompts become the interface for instructing AI to write code, generate tests, manage infrastructure, and more.

5 min read · [iametornam.hashnode.dev](https://iametornam.hashnode.dev/prompt-driven-development-the-next-evolution-in-software-engineering?utm_source=hashnode&utm_medium=feed)

[Jun 24, 2025](https://hashnode.com/posts/prompt-driven-development-the-next-evolution-in-software-engineering/685a90966195e6efc7052b92)
