I Built a $6 Menu Translator Cafes Actually Want (Gemma Local, $0 API Cost)
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built DineLingo — a local-first menu translator a real restaurant would pay for. Type a dish in Hinglish like Masala Dosa - crisp rice crepe, aloo masala → get a tourist-ready line + allergen + veg flag, QR-ready for table tents: Masala Dosa: Crisp rice crepe, aloo masala — crisp rice-lentil crepe with…
This is a report on a unique AI-powered solution called DineLingo, designed to help local cafes overcome language barriers with tourists and non-English-speaking customers. The project won the Hacktoberfest Open-Source AI Challenge in Week 2: Side Hustle category.
DineLingo is a local-first menu translator that allows single-location restaurants with limited English language resources to display translated menus for their customers. The cafes can purchase a one-time license of $6, which translates up to 30 dishes and generates QR codes for the translated menu. The solution is built on open-source AI using Google's Gemma 2.2B model, ensuring no monthly SaaS fees and keeping the translated menu data on the cafe's own device.
The main problem DineLingo addresses is that existing translation apps struggle with accurate dish naming, require an internet connection, and involve sending recipes to uncontrolled servers. DineLingo solves these issues by providing an offline, QR-ready translation service that restaurants can customize to their needs. The tool works on any standard laptop, and the owner can further fine-tune the translations as required.
What sets DineLingo apart is its cost-effectiveness and privacy. Traditional translation APIs charge per character, making the $6 price point for 30 dishes quite competitive. More importantly, by keeping the translated data on the cafe's own device, DineLingo ensures privacy and avoids recurring costs associated with SaaS solutions.
The project is built on open-source AI, specifically Google's Gemma 2.2B model, which is available for free via Hugging Face Transformers. The code is open-source and hosted on GitHub, allowing anyone to access, modify, and contribute to the project. The development process involved creating a Gradio UI for an interactive demo, a Python CLI for offline translation, and an owner-editable phrasebook containing 12 Hinglish-to-English translations.
The main advantage of DineLingo is that it provides a one-time solution without recurring subscriptions, making it a profitable business model for the creators. The offline functionality is a major advantage, ensuring the service remains available even during power outages or internet connectivity issues. Additionally, the owner can edit the phrasebook and fine-tune the translations using Gemma, providing flexibility to adapt to specific restaurant needs.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.