You can deploy this model and start earning money today!

mariannam/
llammas-CER-prediction

Name: llammas-CER-prediction
Availability: InStock

Views

No views yet

Authors

"Ajalooliste eestikeelsete OCR tekstide järeltöötluse ja hindamise automatiseerimine Eesti Rahvusraamatukogu jaoks" (2025, TalTech)

"Automation of Post-Processing and Evaluation of Historical Estonian OCR Texts for the National Library of Estonia"

Loore Lehtmets, Mari-Anna Meimer

Model Description

This model was developed as a Bachelor's thesis at Tallinn University of Technology. It is trained to predict the CER (Character Error Rate) of historical Estonian OCR texts and is primarily intended for use by the National Library of Estonia on materials from their digital archive.

Model Sources

All training and testing code, including datasets and results, is available on GitHub:

Repository: https://github.com/mari-annam/estonian-ocr

Dataset

The model was trained on 9,231 text examples from the digital archive of the National Library of Estonia. These examples consist of OCR-generated text paired with the CER of the OCR text in comparison to human-corrected versions. The model was evaluated on 2,001 separate text examples from the same archive. More information about the datasets and results is available on GitHub and in the thesis document.

How To Use?

To try out the model, copy the example code below into Google Colab or any Python environment. Edit the ocr_text variable with the OCR text you want to get the predicted CER for.

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel, PeftConfig
from huggingface_hub import login

# load model for CER predicting
peft_model_id = "mariannam/llammas-CER-prediction"
config = PeftConfig.from_pretrained(peft_model_id)

# load base model
base_model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    device_map="auto", # for CPU use device_map=None
    torch_dtype="auto"
)

# load adapters
model = PeftModel.from_pretrained(base_model, peft_model_id)

# load tokenizer
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

# input ocr text to get the CER for HERE
ocr_text = "Misso wallas awati awalik telefoni-kõnc-punkt Hinol ja PiiganbiS mõlemal, Kanepi kanbu."

# prompt tempelate
prompt = f"""### Instruction:
Kui suur protsent tähemärke sellest ajaloolisest eestikeelsest tekstist on vigane? Tagasta protsent täisarvuna.

### Input:
{ocr_text}

### Response:
"""

# generate and print output
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=3)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(prompt):].strip())