Stars
A simple Python wrapper and command-line interface for archive.org’s "Save Page Now" capturing service
A configurable jobs.ac.uk job searcher, web scraping then filtering the results with chatgpt
Repository on a series of Experimentations with Optical Character Recognition
Command line tool for extracting text from images using Apple's Vision framework.
A python wrapper to extract text from images on a mac system. Uses the vision framework from Apple.
A powerful command-line OCR tool built with Apple's Vision framework, supporting single image and batch processing with detailed positional information output.
A package for generating synthetic data and fine-tuning a gliner model.
Tutorial for creating a reconciliation service for wikibase.cloud for OpenRefine
Collection of georeferenced boundaries of world countries and cultural regions for use in mapping historical data on global or continental scale
The Implement of "A Lightweight Weak Semantic Framework for Cinematographic Shot Classification"
Official code for our paper "An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction" which will be published at AAAI 2024.
Detecting cinema shot types using a ResNet-50
Science Museum Group Collection Online
Gato Prompt Language (GPL): A system for generating focused instructions and short-form outputs.
awesome synthetic (text) datasets
Transform Unstructured Data into Synthetic Datasets
A command-line application to convert images, PDFs, and audio files to text using Apple's APIs
Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open sourced AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SL…
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Open Video Annotation Project
Python module to query the Smithsonian Institution Open Access API
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.