Lists (3)
Starred repositories
A PyTorch Library for Multi-Task Learning
Resources for spoken Norwegian language
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
A massively multilingual modern encoder language model
This is a simple Python package for calculating a variety of lexical diversity indices
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization [arXiv 2025]
Targetted language identifier, based on FastText and Hunspell.
kpu / fasterText
Forked from facebookresearch/fastTextLibrary for fast text representation and classification.
Hacky, simple version of the Wikidata Graph Builder just for lexemes
Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages (ACL 2025)
A collection of raw text from various Greek dialects
Improved Sentence Alignment in Linear Time and Space
Fast inference engine for Transformer models
Modules to convert numbers to words. 42 --> forty-two
Hunspell Live is an open-source customized spell-checking tool powered by Spylls.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
Effortless Real-Time Sign Language Translation
Meta's "No Language Left Behind" models served as web app and REST API
A library for efficient similarity search and clustering of dense vectors.
Repository for "Bitext Mining for Low-Resource Languages via Contrastive Learning"
An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"
A unified interface for computing surprisal (log probabilities) from language models! Supports neural, symbolic, and black-box API models.
Javascript Virtual Keyboard - Customizable, responsive and lightweight