Create app_summaries_longdoc.py

app_summaries_longdoc.py

@@ -0,0 +1,58 @@
+import nltk
+
+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)