DadmaTools is a Persian NLP tools developed by Dadmatech Co.

Indian Language Tagger and Chunker (Hindi, Telugu, Tamil, Marathi, Punjabi, Kanada, Malayalam, Urdu, Bengali)

A recursive text chunker that attempts to break the text on meaningful boundaries.

The primary purpose of this tool is to make it easier to input long YouTube transcripts into ChatGPT by splitting them into smaller chunks. Additionally, prompt-engineering techniques have been incorporated to improve the quality of the output.

A collection of useful small python helpers

A sentence chunker PHP class + visualizer for Berkeley Parser parse trees

Contains implementation of models like BiLSTM CRF, Hierarchical BiLSTM for POS Tagging.

A Processing Toolbox for Persian Texts

Lazily split an array into chunks, just like slices of pizza 🍕

This is a simple project of building custom training and model data for Apache OpeNLP library. The main task is recognizing Ukrainian texts and building helpful questions and theses.

This repository contains Natural Language Processing programs in the Python programming language.

Rabin IPFS chunker in rust/wasm