BELT (BERT For Longer Texts). BERT-based text classification model for processing texts longer than 512 tokens.
Python client for Cognica database
Generalist model for Relation Extraction (Extract any relation types from texts)
70+ beginner to intermediate level questions on CLI text processing tasks
Puristaa (Finnish for compress) - shared prefix compression of ordered string sequences.
A library for processing Code Mixed Text. Still in development!
Pyline is a grep-like, sed-like, awk-like command-line tool for line-based text processing in Python.
A Framework for Integrating Linguistic Analysis and Semantic Annotation of Text Documents.
A CLI tool for interacting with the Vectara platform, including advanced text processing and indexing features.
A Python library for processing Yiddish text
Voice-Activated Natural Language UI
MoverScore: Evaluating text generation with contextualized embeddings and earth mover distance
CausalNLP: A Practical Toolkit for Causal Inference with Text
A text-in parser engine for document processing
Snips Natural Language Understanding library
Melusine is a high-level library for emails processing
Python library for SEO-friendly HTML text processing and keyword linking
Bloatectomy: a method for the identification and removal of duplicate text in the bloated notes of electronic health records and other documents.
A package for CLIP-based image and text processing.
A system that translates natural language queries into programmatic actions
dummy csv, flat, json text file generator, typical usage scenario can be load / stress / performance testing of file-processing data tools
indxr: A Python utility for indexing long files.
Pre-processing text in parallel for Keras in python.
A Python package for extracting and processing text from images.
Test package for distribution
Simplifies arranging text fragments with multiple speakers and processing it with coqui.ai TTS
Natural Language Understanding (text processing) for math symbols, digits, and words with a Gradio user interface and REST API.
pdfalign is a very simple tool to grid align extracted pdf text. This is useful for invoice table extraction or further processing with llms / rag systems
Fast text processing acceleration.
Python interface for eunjeon project & mecab based morphological analyzer.
Rotate and combine tables (Danish: Roter og kombiner borde).
nlp library which support text processing methods, text match methods, etc.
Tokenizing and processing text inputs with transformer models
Processes PDF files through various scripts to extract, clean, format and export text from a PDF file
Tiny preprocessor for Russian text
Text Embeddings Inference (TEI)'s unofficial python wrapper library for batch processing with asyncio
State of the art toolchain for natural language processing in French
Python port of open source text processing library for Turkish, zemberek-nlp
Text processing tool for detecting Danish CPR-numbers.
中文情感分析库(Chinese Sentiment))可对文本进行情绪分析、正负情感分析。
Paxter is a document-first, text pre-processing mini-language toolchain, loosely inspired by @-expressions in Racket
Pashto Natural Language Processing Toolkit
Biome-text is a light-weight open source Natural Language Processing toolbox built with AllenNLP
Artless and small template library for server-side rendering.