Showing 41-60 of 173 projects
Porcupine is an on-device wake word detection library powered by deep learning, enabling hands-free voice activation in AI apps.
An open-source office suite with tools to work with documents, spreadsheets, presentations, PDFs, and PDF forms on multiple platforms.
This repo contains a list of the 10,000 most common English words, useful for NLP and language modeling tasks.
A tool that simplifies the process of pasting Markdown and AI responses (ChatGPT/DeepSeek) into common productivity apps like Word, WPS, and Excel.
A Chinese NLP library for tokenization, part-of-speech tagging, named entity recognition, and lexical analysis.
A PDF toolbox for Anki that helps developers efficiently convert knowledge from various sources into flashcards.
A JavaScript library for creating interactive word clouds using the D3.js visualization framework.
A JavaScript library for generating Microsoft Office documents (Word, PowerPoint, Excel) from templates.
A Kotlin multiplatform app that helps users learn English words in the context of movies, TV shows, and documents.
Jiagu is a deep learning-based NLP toolkit that provides features like Chinese word segmentation, NER, sentiment analysis, and more.
SymSpell is a lightning-fast library for spelling correction and fuzzy text search using the Symmetric Delete algorithm.
A C++ library for detecting custom wake words using a deep neural network, useful for AI voice assistants.
A library for training multilingual word embeddings, useful for NLP tasks across languages.
A Node.js library for Chinese word segmentation, providing a simple and efficient way to tokenize Chinese text.
An open-source Chinese NLP library providing state-of-the-art tools for word segmentation, dependency parsing, named entity recognition, and more.
A collection of commonly used CSS class names to help developers build user interfaces more efficiently.
A continuously updated Chinese sensitive word library to help developers and content reviewers quickly identify and filter inappropriate text.
LDA2Vec is a Python library for topic modeling and word embeddings, useful for vibe coders building AI-powered applications.
A multi-purpose screenshot, OCR, and translation software tool for developers working with AI tools.
Top2Vec learns jointly embedded topic, document and word vectors for semantic search and topic modeling.
Get weekly updates on trending AI coding tools and projects.