Neural network trained to translate from ancient languages to modern languages

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Truly minimal Docker images for Hugo open-source static site generator.

LLM inference in C/C++

A SQLite extension which loads a Google Sheet as a virtual table.

(subjective) overview of projects which are related both to python and semantic technologies (RDF, OWL, Reasoning, ...)

Making it easy to query APIs via SQL

A Python project for generating badges for your projects, with a focus on simplicity and flexibility.

MateCat is an AI driven translation tool for language industry professionals. Matecat makes machine translation post-editing and project outsourcing easy.

An Integrated Corpus Tool With Multilingual Support for the Study of Language, Literature, and Translation

The most intuitive Static Site CMS designed for SEO-optimized and privacy-focused websites.

Tesseract Open Source OCR Engine (main repository)

Machine-Translation-based sentence alignment tool for parallel text

Code for our paper in ACL 2017

My graduation project in THU

🏭 PDF text extraction pipeline: self-hosted, local-first, Docker-based

📜 Dehyphenation of broken text (mainly German), i.e., extracted from a PDF

A simple plugin to add JSON Web Token (JWT) Authentication to WP REST API

advertools - online marketing productivity and analysis tools

Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.

🎨 A utility for converting images to text art.

Elegant, modern and asynchronous Telegram MTProto API framework in Python for users and bots

Jazzy theme for Django

IntelOwl: manage your Threat Intelligence at scale

Python version of the Playwright testing and automation library.

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

ELK stack in docker images configured to analyze GoogleBot activity on your website

Extract dates from text

Code to legally and automatically print your purchased e-books from VitalSource.com

An advanced open-source publishing and revenue-generating platform for news organizations.