mbart_50_SinhalaTransliteration

mBART-50 Sinhala Transliteration Model

This model transliterates Romanized Sinhala text to Sinhala script.

Model description

This is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt specialized for Sinhala transliteration. It converts romanized Sinhala (using Latin characters) to proper Sinhala script.

Intended uses & limitations

This model is intended for transliterating Romanized Sinhala text to proper Sinhala script. It can be useful for:

• Text input conversion in applications
• Helping non-native speakers type in Sinhala
• Converting legacy text in romanized format to proper Sinhala

How to use

from transformers import MBartForConditionalGeneration, MBartTokenizerFast

# Load model and tokenizer
model_name = "deshanksuman/mbart_50_SinhalaTransliteration"
tokenizer = MBartTokenizerFast.from_pretrained(model_name)
model = MBartForConditionalGeneration.from_pretrained(model_name)

# Set language codes
tokenizer.src_lang = "en_XX"  # Using English as source language token
tokenizer.tgt_lang = "si_LK"  # Sinhala as target

# Prepare input
text = "heta api mkda krnne"
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=96,
    num_beams=5,
    early_stopping=True
)

# Decode output
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)

Training data

The model was trained on the deshanksuman/SwaBhasha_Transliteration_Sinhala dataset, which contains pairs of Romanized Sinhala and corresponding Sinhala script text.

Training procedure

The model was trained with the following parameters:

• Learning rate: 5e-05
• Batch size: 16
• Number of epochs: 2
• Max sequence length: 128
• Optimizer: AdamW

This is trained for sentence level.

Examples:

Example 1:

• Romanized: Dakunu koreyawe eithihasika
• Expected: දකුණු කොරියාවේ ඓතිහාසික
• Predicted: දකුණු කොරියාවේ ඓතිහාසික
• Correct: True

Example 2:

• Romanized: Okoma hodai ganu gathiya
• Expected: ඔක්කොම හොදයි ගෑනු ගතිය
• Predicted: ඕකම හොදයි ගනු ගතිය
• Correct: False

Example 3:

• Romanized: Malki akkith ennwa nedenntm godak kemathiyakkila dennm supiriyatam dance
• Expected: මල්කි අක්කිත් එනව නෙදෙන්නටම ගොඩක් කෑමතියිඅක්කිල දෙන්නම සුපිරියටම ඩාන්ස්
• Predicted: මල්කි අක්කිත් එන්නව නෑද්දෑන්ත්ම ගොඩක් කෑමතියිඅකිල දෑන්ඩම් සුපිරියටම ඩාන්ස්
• Correct: False

Citation

@article{sumanathilaka2025swa,
  title={Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources},
  author={Sumanathilaka, Deshan and Perera, Sameera and Dharmasiri, Sachithya and Athukorala, Maneesha and Herath, Anuja Dilrukshi and Dias, Rukshan and Gamage, Pasindu and Weerasinghe, Ruvan and Priyadarshana, YHPP},
  journal={arXiv preprint arXiv:2507.09245},
  year={2025}
}