WindstormLabs/origin-Helsinki-NLP-opus-mt-caenes-eo

from transformers import MarianMTModel, MarianTokenizer
import torch

model_name = "Helsinki-NLP/opus-mt-caenes-eo"

device = "cuda" if torch.cuda.is_available() else "cpu"
model = MarianMTModel.from_pretrained(model_name).to(device)
tokenizer = MarianTokenizer.from_pretrained(model_name)

source_texts = [
	"Buenos días, qué tal?",
	"Bon dia, com estàs?",
	"Good morning, how are you?"
	]

inputs = tokenizer(source_texts, return_tensors="pt", padding=True, truncation=True)
inputs = {k: v.to(device) for k, v in inputs.items()}

translated_ids = model.generate(inputs["input_ids"])
translated_texts = tokenizer.batch_decode(translated_ids, skip_special_tokens=True)

for src, tgt in zip(source_texts, translated_texts):
    print(f"Source: {src} => Translated: {tgt}")