Skip to content
Change the repository type filter

All

    Repositories list

    • marie-ai

      Public
      Complex data extraction and orchestration framework designed for processing unstructured documents. It integrates AI-powered document pipelines (GenAI, LLM, VLLM) into your applications, supporting various tasks such as document cleanup, optical character recognition (OCR), classification, splitting, named entity recognition, and form processing
      Python
      MIT License
      563653Updated Jan 8, 2025Jan 8, 2025
    • fairseq

      Public
      Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
      Python
      MIT License
      6.4k000Updated Nov 26, 2024Nov 26, 2024
    • fastwer

      Public
      A PyPI package for fast word/character error rate (WER/CER) calculation
      Python
      MIT License
      15000Updated Nov 20, 2024Nov 20, 2024
    • layoutex

      Public
      Synthetic Document Generator for document cleanup and annotation free layout analysis
      Python
      MIT License
      1101Updated Nov 21, 2023Nov 21, 2023
    • Marie-AI Server
      Python
      0200Updated Mar 14, 2023Mar 14, 2023