BART-large-ocr

This model is released as part of the paper Leveraging LLMs for Post-OCR Correction of Historical Newspapers and designed to correct OCR text. BART-large is fine-tuned for post-OCR correction of historical English, using BLN600, a parallel corpus of 19th century newspaper machine/human transcription.

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline

model = AutoModelForSeq2SeqLM.from_pretrained('pykale/bart-large-ocr')
tokenizer = AutoTokenizer.from_pretrained('pykale/bart-large-ocr')
generator = pipeline('text2text-generation', model=model.to('cuda'), tokenizer=tokenizer, device='cuda', max_length=1024)

ocr = "The defendant wits'fined �5 and costs."
pred = generator(ocr)[0]['generated_text']
print(pred)

Citation

@inproceedings{thomas-etal-2024-leveraging,
    title = "Leveraging {LLM}s for Post-{OCR} Correction of Historical Newspapers",
    author = "Thomas, Alan and Gaizauskas, Robert and Lu, Haiping",
    editor = "Sprugnoli, Rachele and Passarotti, Marco",
    booktitle = "Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024",
    month = "may",
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lt4hala-1.14",
    pages = "116--121",
}