Spark-it
Partager le stage
Description :
This project aims to develop an AI-driven system that extracts and interprets text from scanned documents, images, andPDFs using advanced NLP and CV technologies. By integrating models like Llama 3.2 Vision or Claude 3.5 Sonnet, the system will process raw data, perform imagerecognition, and apply NLP techniques to categorize the extracted information. The goal is to automate data extraction, reducing manual effort and improving reliability for applications such asdocument digitization and data entry automation.
Missions :
Requirement :
Python, Hugging Face Transformers, spaCy, NLTK, OpenCV, TensorFlow, PyTorch, Tesseract OCR, EasyOCR
Date d’expiration: 12 décembre, 2024
Date d’expiration: 12 décembre, 2024