Building Zubro – a voice-first English tutor on Google’s Gemini Live API

Posted on by Tomek

What is Zubro?

Zubro - a European bison with headphones and a green scarf

This article was created for the purposes of entering the Gemini Live Agent Challenge hackathon. #GeminiLiveAgentChallenge

Zubro is a voice-first English learning companion. You talk, Zubro listens, responds, corrects your grammar, and adapts to your level – all through real-time voice conversation. No typing, no multiple choice, no textbook exercises. Just a conversation with a patient AI tutor who happens to be a European bison wearing a green scarf.

A quick note on the name. In Polish, żubr (pronounced roughly “zhoobr”) means European bison – a national symbol and the largest land animal in Europe. I took the dot above the ż in the original Polish spelling, moved it to the end of the word, and got zubro. A slightly mangled version of a Polish word, used to teach English. Felt appropriate.

 

Continue reading →

Fine-Tuning Embedding Models: A Practical Guide with EmbeddingGemma

Posted on by Tomek

This guide walks you through the theory and practice of fine-tuning embedding models using EmbeddingGemma as an example. If you’d rather skip the explanations and jump straight into code, I’ve prepared a Colab notebook you can run yourself — it’s well-documented and takes about 10-20 minutes with GPU enabled.

Still here? Great, let’s start with the basics.

Fine-tuning Embedding Models

What is fine-tuning and why bother?

Pre-trained models are generalists. They’ve seen billions of words and learned what “similar” means across the entire internet. That’s impressive — but it’s also the problem. Your domain has its own vocabulary, its own acronyms, its own meaning of words that the rest of the world uses differently.

Fine-tuning is the process of taking a pre-trained model and teaching it the nuances of your specific world. Instead of training from scratch (expensive, slow, requires massive data), you start with a model that already understands language and nudge it toward your use case. Think of it as hiring someone with great general skills and then onboarding them to your company’s way of doing things.

Continue reading →

Unlocking Unstructured Data Potential with Google Gemini 1.0 Pro

Posted on by Tomek

In today’s digital era, businesses across the globe are inundated with vast oceans of unstructured data. From emails and documents to social media posts and beyond, this data holds invaluable insights that can drive innovation, enhance customer satisfaction, and streamline operations. However, the sheer volume and complexity of unstructured data present significant challenges in terms of analysis and information retrieval. Traditional data processing tools often fall short when faced with the nuanced, irregular, and often unpredictable nature of this data.

Enter Google Gemini 1.0 Pro, a cutting-edge Generative AI Model. In this article I would like to propose an intriguing way of utilizing such models to navigate the labyrinth of unstructured data with unprecedented ease and efficiency. By leveraging the power of Gemini 1.0 Pro, businesses can transform their data analysis processes, uncovering the hidden gems of information that lie buried within the digital textual chaos.

Continue reading →