app.py

import gradio as gr
import torch
from transformers import BertTokenizerFast, EncoderDecoderModel

device = 'cuda' if torch.cuda.is_available() else 'cpu'
ckpt = "csebuetnlp/mT5_multilingual_XLSum"
tokenizer = BertTokenizerFast.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
model = EncoderDecoderModel.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")

def generate_summary(text):

   inputs = tokenizer([text], padding="max_length", truncation=True, max_length=512, return_tensors="pt")
   input_ids = inputs.input_ids.to(device)
   attention_mask = inputs.attention_mask.to(device)
   output = model.generate(input_ids, attention_mask=attention_mask)
   return tokenizer.decode(output[0], skip_special_tokens=True)

demo = gr.Interface(fn=generate_summary,
                    inputs=gr.Textbox(lines=10, placeholder="Insert the text here"),
                    outputs=gr.Textbox(lines=4)
                    )

demo.launch()