Stars
Front Matter is a CMS running straight in Visual Studio Code. Can be used with static site generators like Hugo, Jekyll, Hexo, NextJs, Gatsby, and many more...
Wan: Open and Advanced Large-Scale Video Generative Models
This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.
For some editions of Wiktionary, extract translation pairs on each page.
A web application component that provides a faceted search interface for bibliographies managed with Zotero.
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
An open etymology dataset created using Wiktionary data. Contains 3.8M entries, 1.8M terms, 2900 languages, and 31 unique relationship types.
BDPROTO: a database of phonological inventories from ancient and reconstructed languages
Robust Speech Recognition via Large-Scale Weak Supervision
Mobile application for Audiobookshelf
đź““ obsidian-compatible notes theme for hugo, built from quartz and hugo-book
đź“ť Easily manage your bibliography and in-text citations with Hugo, the popular static-site generator.
Tracking instruction-tuned LLM openness. Paper: Liesenfeld, Andreas, Alianda Lopez, and Mark Dingemanse. 2023. “Opening up ChatGPT: Tracking Openness, Transparency, and Accountability in Instructio…
Wiktionary dump file parser and multilingual data extractor
LingPy: Python library for quantitative tasks in historical linguistics
Neural Language Models for Historical Research
A Python module to discover the etymology of words
A suite of Arabic natural language processing tools developed by the CAMeL Lab at New York University Abu Dhabi.