app.py

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

MODEL_NAME = "angkor96/khmer-news-summarization"

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME).to(device)
model.eval()

def summarize(text):
    try:
        inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=1024)
        inputs = {k: v.to(device) for k, v in inputs.items()}
        with torch.no_grad():
            summary_ids = model.generate(
                **inputs,
                max_length=150,
                num_beams=4,
                length_penalty=2.0,
                early_stopping=True
            )
        return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
    except Exception as e:
        return f"មិនអាចសង្ខេបបានទេ។ ({e})"

iface = gr.Interface(
    fn=summarize,
    inputs=gr.Textbox(label="បញ្ចូលអត្ថបទ"),
    outputs=gr.Textbox(label="អត្ថបទសង្ខេប"),
    title="Khmer News Summarization API",
    description="API service powered by angkor96/khmer-news-summarization",
    api_name="predict",  # <-- this exposes /run/predict
)

iface.launch()