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

device = 'cuda' if torch.cuda.is_available() else 'cpu'
ckpt = 'mrm8488/bert2bert_shared-spanish-finetuned-summarization'
tokenizer = BertTokenizerFast.from_pretrained(ckpt)
model = EncoderDecoderModel.from_pretrained(ckpt).to(device)

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)


textbox = gr.Textbox(placeholder="Introduzca texto a resumir ...", lines=4)
demo = gr.Interface(fn=generate_summary, inputs=textbox,outputs="text")

demo.launch()