shanndrea/indot5-small-penyederhanaan-teks-medis

Indonesian Medical Text Simplifier

This model is fine-tuned from indobenchmark/indot5-small for the task of medical text simplification in the Indonesian language.

How to Use

from transformers import T5ForConditionalGeneration, T5Tokenizer

model_name = "shanndrea/indot5-small-penyederhanaan-teks-medis"
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)

def simplify(text):
    prompt = "sederhanakan: " + text
    inputs = tokenizer(prompt, return_tensors="pt", max_length=128, truncation=True)
    outputs = model.generate(
        inputs.input_ids, 
        max_length=128, 
        num_beams=5,
        early_stopping=True
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Example usage
complex_text = "Pasien mengeluhkan mialgia setelah melakukan aktivitas fisik yang berlebihan."
simplified_text = simplify(complex_text)
print(f"Complex Sentence: {complex_text}")
print(f"Simplified Sentence: {simplified_text}")