Skip to content
View tomvlt1's full-sized avatar

Highlights

  • Pro

Block or report tomvlt1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tomvlt1/README.md

Hey, I'm Tom.

IE Business School, London, Madrid, Paris. Dual Business + Data Analytics.

Building.

Projects

  • madrid-rental-vision — can a photo tell you how much a flat rents for? About +0.05 R² says yes. Ships with a Chrome extension and a Next.js dashboard on top of the model.
  • bullseye — Chrome extension that fact-checks highlighted text with a confidence score and supporting / contradicting sources. Manifest V3.
  • speaker-verification — I wanted a way to grade class participation from the actual audio of the class, not from professor memory. Wraps Azure Speaker Recognition.
  • Lock-in — iOS habit tracker I built to keep myself accountable. Sideload via Sideloadly.

Stack

Python (PyTorch, scikit-learn, FastAPI) · Swift (SwiftUI, SwiftData) · TypeScript (React, Next.js, React Native) · Supabase · a bit of everything.

Reach

Pinned Loading

  1. Lock-in Lock-in Public

    iOS habit tracker I built to get my shit together. SwiftUI + SwiftData, fully on-device, sideload via Sideloadly.

    Swift 1

  2. madrid-rental-vision madrid-rental-vision Public

    Can a photo tell you how much a flat rents for? On 6,047 Madrid listings, R² 0.88 and €274 MAE say yes. SigLIP image embeddings + multilingual text + gradient boosting (5-fold CV). Ships with a Chr…

    Python

  3. speaker-verification speaker-verification Public

    Grade class participation from lecture recordings instead of professor memory. Identifies enrolled speakers via Azure Speaker Recognition. Bring-your-own audio.

    Python

  4. bullseye bullseye Public

    Chrome extension that fact-checks highlighted text with a confidence score and supporting/contradicting sources. Manifest V3, bring-your-own backend.

    JavaScript