#nlp

Fast Cantonese text-to-Jyutping (G2P) — Rust core, Python (PyO3). Numbers, dates, and HK English code-switching.

Multilingual, context-aware abbreviation expansion for text normalization and speech.

A specialist Python toolkit for Ancient Greek - alphabetic Greek NLP (incl. a neural pipeline) and the Aegean syllabic scripts (Linear A, Linear B, Cypriot, Cypro-Minoan)

English Part-of-Speech Tagger Library; a Ruby port of Lingua::EN::Tagger

Node.js bindings for the NLP++ text-analysis engine (npm peer of the Python package NLPPlus)

A high performance Rust-based Chinese text converter that performs word segmentation using Jieba and OpenCC lexicons.

HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382

A command-line tool to extract plain text from Wikipedia dumps with category and section filtering

Smart expansion of Spanish legal acronyms. 647 verified acronyms from RAE, BOE and DPEJ. | Expansión inteligente de siglas legales españolas.

Pre-built Snowball stemmers for Rust (tracks snowball main)

Provider-agnostic Go AI framework for building RAG, agents, and AI-powered applications. Swap LLM providers without code changes — supports Ollama, OpenAI, and more.

Rust implementation of the Mistral Tekken tokenizer

A Rust port of Microsoft Presidio — PII detection & anonymization (analyzer + anonymizer + Python bindings)

🔤 Natural language detection for Elixir without AI

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

Language model tokenization at GB/s

Calculate syllable count for English words.