OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

pipreqs - Generate pip requirements.txt file based on imports of any project. Looking for maintainers to move this project forward.

Pythonic AI generation of images and videos

A library of translation-based text similarity measures

State of the Art Natural Language Processing

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

List of Python API Wrappers and Libraries

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

VSCode extension that generates docstrings for python files

Py4J enables Python programs to dynamically access arbitrary Java objects

An Open-Source Python3 tool for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conv…

pix2tex: Using a ViT to convert images of equations into LaTeX code.

A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

Fine-tuning Mistral LLM for Adaptive Machine Translation

A Hierarchically-Labeled Portuguese Hate Speech Dataset

PorSimplesSent - A Portuguese corpus of aligned sentences pairs to investigate sentence readability assessment

Portuguese translation of the GLUE benchmark and Scitail dataset

Fine tuning of the Retrieval-Augmented Generation (RAG) with a custom knowledge source.

List of resources and tools developed with focus on Portuguese.

Apache Hive

Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks

Apache Hadoop

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

Python client for Apache Kafka

The Hugging Face course on Transformers

Trax — Deep Learning with Clear Code and Speed

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Python job scheduling for humans.

Open Source Neural Machine Translation and (Large) Language Models in PyTorch

OpenRefine is a free, open source power tool for working with messy data and improving it