app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

# model 불러오기
model_name = "gj5520/kkachi60_en2ko"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device).eval()

# 번역 함수
def translate(text: str):
    prefix = "translate English to Korean: "
    inputs = tokenizer(prefix + text,
                       return_tensors="pt",
                       truncation=True,
                       padding="longest").to(device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        num_beams=5,
        no_repeat_ngram_size=3,
        early_stopping=True,
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Gradio 인터페이스 정의
interface = gr.Interface(
    fn=translate,
    inputs=gr.Textbox(
        lines=3,
        placeholder="Enter English text here..."
    ),
    outputs="text",
    title="영어→한국어 번역기 (kkachi60_en2ko)",
    description="Hugging Face kkachi60_en2ko 모델을 사용한 실시간 번역"
)

# Spaces에서 자동 실행
if __name__ == "__main__":
    interface.launch()