ByT5-Small-fine-tuned2

import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("savinugunarathna/ByT5-Small-fine-tuned2")
model = AutoModelForSeq2SeqLM.from_pretrained("savinugunarathna/ByT5-Small-fine-tuned2")

device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device).eval()

def translate(text: str) -> str:
    prompt = f"translate Singlish to Sinhala: {text}"
    inputs = tokenizer(prompt, return_tensors="pt", max_length=512, truncation=True).to(device)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=128, num_beams=4)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Interactive loop — type 0 to exit
while True:
    user_input = input("Singlish: ").strip()
    if user_input == "0":
        break
    if user_input:
        print(f"Sinhala:  {translate(user_input)}\n")

@misc{gunarathna2025byt5singlish,
  title={ByT5-Small Singlish to Sinhala: A Three-Phase Curriculum Approach with LoRA Fine-Tuning},
  author={Gunarathna, Savinu},
  year={2025},
  howpublished={Hugging Face Model Hub},
  note={\url{https://huggingface.co/savinugunarathna/ByT5-Small-fine-tuned2}}
}

@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}
}

@inproceedings{Nsina2024,
  author={Hettiarachchi, Hansi and Premasiri, Damith and Uyangodage, Lasitha and Ranasinghe, Tharindu},
  title={{NSINA: A News Corpus for Sinhala}},
  booktitle={The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  year={2024},
  month={May},
}

@article{ranasinghe2022sold,
  title={SOLD: Sinhala Offensive Language Dataset},
  author={Ranasinghe, Tharindu and Anuradha, Isuri and Premasiri, Damith and Silva, Kanishka and Hettiarachchi, Hansi and Uyangodage, Lasitha and Zampieri, Marcos},
  journal={arXiv preprint arXiv:2212.00851},
  year={2022}
}