example.py

from transformers import MBartForConditionalGeneration, MBartTokenizer

def transliterate(text, model_name="deshanksuman/swabhashambert50SinhalaTransliteration"):
    # Load model and tokenizer
    tokenizer = MBartTokenizer.from_pretrained(model_name)
    model = MBartForConditionalGeneration.from_pretrained(model_name)
    
    # Set the language codes
    tokenizer.src_lang = "en_XX"
    tokenizer.tgt_lang = "si_LK"
    
    # Prepare input
    inputs = tokenizer(
        text,
        return_tensors="pt",
        max_length=128,
        padding="max_length",
        truncation=True
    )
    
    # Generate output
    outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        max_length=128,
        num_beams=5,
        early_stopping=True
    )
    
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Example usage
if __name__ == "__main__":
    # Test with example text
    test_text = "mama oyata adare karanawa"
    result = transliterate(test_text)
    print(f"Romanized: {test_text}")
    print(f"Transliterated: {result}")