IEEE

Robust Optical Character Recognition Using DenseNet121: Leveraging Google Fonts for Dataset Diversity

Abstract: This research study presents the application of the DenseNet121 model for Optical Character Recognition (OCR) using a dataset generated from 3,475 Google Fonts, encompassing 62 classes of ...
GitHub

A minimal, secure Python interpreter written in Rust for use by AI.

Experimental - This project is still in development, and not ready for the prime time. A minimal, secure Python interpreter written in Rust for use by AI. Monty avoids the cost, latency, complexity ...
IEEE

AIvaluate: A Multi-Agent Framework for Automated Answer Script Evaluation Using Large Language Models and Semantic Vector Indexing

Abstract: In conventional educational environments, it is labor-intensive, subjective, and susceptible to human error to hand-mark descriptive answers. This article ...

Speechify's AI Voice Research Lab Launches SIMBA 3.0 Voice Model to Power Next Generation of Voice AI

Speechify's Voice AI Research Lab Launches SIMBA 3.0 Voice Model to Power Next Generation of Voice AI SIMBA 3.0 represents a major step forward in production voice AI. It is built voice-first for ...
GitHub

Translate PDFs using OCR and machine translation—supports both scanned documents and digital PDFs.

This tool extracts text from PDF pages using Surya OCR (for scanned documents) or PyMuPDF (for digital PDFs), translates it via Google Translate, and renders the translated text back onto the original ...