from transformers import NllbTokenizer, AutoModelForSeq2SeqLM

model_name = "keithtwesigye/lunyoro-nllb_en2lun"
tokenizer = NllbTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

tokenizer.src_lang = "eng_Latn"
text = "How are you?"
inputs = tokenizer(text, return_tensors="pt", truncation=True)
output = model.generate(
    **inputs,
    forced_bos_token_id=tokenizer.convert_tokens_to_ids("run_Latn"),
    num_beams=4,
    max_length=256
)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Related Models

Model	Description
lunyoro-en2lun	MarianMT English → Lunyoro
lunyoro-lun2en	MarianMT Lunyoro → English
lunyoro-nllb_en2lun	NLLB-200 English → Lunyoro
lunyoro-nllb_lun2en	NLLB-200 Lunyoro → English

Full Application

Source code: chriskagenda/TRANSLATOR

keithtwesigye/lunyoro-nllb-en2lun

lunyoro-nllb_en2lun

Model Details

Dataset

Usage

Related Models

Full Application

keithtwesigye/
lunyoro-nllb-en2lun