small-100-Singlish-Sinhala-CodeMix

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id  = "savinugunarathna/small-100-Singlish-Sinhala-CodeMix"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model     = AutoModelForSeq2SeqLM.from_pretrained(model_id)

tokenizer.src_lang = "en"
tgt_lang_id = tokenizer.lang_code_to_id["si"]

def translate(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
    output = model.generate(
        **inputs,
        forced_bos_token_id=tgt_lang_id,
        num_beams=3,
        max_new_tokens=128,
        repetition_penalty=1.2,
    )
    decoded = tokenizer.decode(output[0], skip_special_tokens=True).strip()
    if decoded.startswith("__si__"):
        decoded = decoded[len("__si__"):].strip()
    return decoded

print(translate("mama hungry, kanna yamu"))
# → මම බඩගිනි, කන්න යමු