app.py

import nltk
import streamlit as st

nltk.download('punkt')

def fragment_text(text, tokenizer):

  sentences = nltk.tokenize.sent_tokenize(text)
  max_len = tokenizer.max_len_single_sentence

  chunks = []
  chunk = ""
  count = -1

  for sentence in sentences:
    count += 1
    combined_length = len(tokenizer.tokenize(sentence)) + len(chunk)

    if combined_length <= max_len:
      chunk += sentence + " "
    else:
      chunks.append(chunk.strip())
      chunk = sentence + " "

  if chunk != "":
    chunks.append(chunk.strip())

  return chunks

def summarize_text(text):

  chunks = fragment_text(text, tokenizer)

  summaries = []
  for chunk in chunks:
    input = tokenizer(chunk, return_tensors='pt')
    output = model.generate(**input)
    summary = tokenizer.decode(*output, skip_special_tokens=True)
    summaries.append(summary)

  final_summary = " ".join(summaries)
  return final_summary

# Importa o modelo de sumarização
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# Define o modelo de sumarização
checkpoint = "tclopess/bart_samsum"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)


text_input = st.text_area("Cole ou digite o texto a ser resumido:")

button = st.button("Resumo")

# Chama a função de sumarização se o botão for clicado
if button:
  summary = summarize_text(text_input)
  st.write("Resumo:")
  st.write(summary)