Trocr Medieval Base

🚀 trc-medieval-base

This is a TrOCR model designed for medieval scripts in the CATMuS Dataset. It aims to convert medieval handwritten images into text, providing a solution for historical document digitization.

🚀 Quick Start

Prerequisites

• Python environment
• Necessary libraries installed (e.g., transformers, PIL, requests)

Steps

1. Install the required libraries:

pip install transformers pillow requests

2. Use the provided Python code to run the model:

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import requests

# load image from the IAM database
url = 'https://huggingface.co/medieval-data/trocr-medieval-print/resolve/main/images/print-1.png'
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

processor = TrOCRProcessor.from_pretrained('medieval-data/trocr-medieval-base')
model = VisionEncoderDecoderModel.from_pretrained('medieval-data/trocr-medieval-base')
pixel_values = processor(images=image, return_tensors="pt").pixel_values

generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

✨ Features

• High Accuracy: With a CER (Character Error Rate) of 0.035, it shows high accuracy in recognizing medieval scripts.
• Based on Pre - trained Model: Built on the microsoft/trocr-base-handwritten base model.
• Specific Dataset: Trained on the CATMuS dataset, which is specifically for medieval scripts.

💻 Usage Examples

Basic Usage

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import requests

# load image from the IAM database
url = 'https://huggingface.co/medieval-data/trocr-medieval-print/resolve/main/images/print-1.png'
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

processor = TrOCRProcessor.from_pretrained('medieval-data/trocr-medieval-base')
model = VisionEncoderDecoderModel.from_pretrained('medieval-data/trocr-medieval-base')
pixel_values = processor(images=image, return_tensors="pt").pixel_values

generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

📚 Documentation

Model Information

Model Status

The model has not been formally tested. Preliminary examination indicates that further finetuning is needed. Finetuning was done with finetune.py found in this repository.

📄 License

This project is licensed under the MIT license.

📚 BibTeX entry and citation info

TrOCR Paper

@misc{li2021trocr,
      title={TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models}, 
      author={Minghao Li and Tengchao Lv and Lei Cui and Yijuan Lu and Dinei Florencio and Cha Zhang and Zhoujun Li and Furu Wei},
      year={2021},
      eprint={2109.10282},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

CATMuS Paper

@unpublished{clerice:hal-04453952,
  TITLE = {{CATMuS Medieval: A multilingual large-scale cross-century dataset in Latin script for handwritten text recognition and beyond}},
  AUTHOR = {Cl{\'e}rice, Thibault and Pinche, Ariane and Vlachou-Efstathiou, Malamatenia and Chagu{\'e}, Alix and Camps, Jean-Baptiste and Gille-Levenson, Matthias and Brisville-Fertin, Olivier and Fischer, Franz and Gervers, Michaels and Boutreux, Agn{\`e}s and Manton, Avery and Gabay, Simon and O'Connor, Patricia and Haverals, Wouter and Kestemont, Mike and Vandyck, Caroline and Kiessling, Benjamin},
  URL = {https://inria.hal.science/hal-04453952},
  NOTE = {working paper or preprint},
  YEAR = {2024},
  MONTH = Feb,
  KEYWORDS = {Historical sources ; medieval manuscripts ; Latin scripts ; benchmarking dataset ; multilingual ; handwritten text recognition},
  PDF = {https://inria.hal.science/hal-04453952/file/ICDAR24___CATMUS_Medieval-1.pdf},
  HAL_ID = {hal-04453952},
  HAL_VERSION = {v1},
}