Update app.py

app.py

@@ -29,42 +29,16 @@ print('Using model {}\n'.format(model_name))
 
 
 def lincoln(content):
-  summary_text = ""
-  for i, paragraph in enumerate(content.split("\n\n")):
-      # get rid of empty paragraphs and one word paras and extra whitespaces
-      paragraph = paragraph.replace('\n',' ')
-      paragraph = paragraph.replace('\t','')
-      paragraph = ' '.join(paragraph.split())
-      # count words in the paragraph and exclude if less than 4 words
-      tokens = word_tokenize(paragraph)
-      # only do real words
-      tokens = [word for word in tokens if word.isalpha()]
-      # print("\nTokens: {}\n".format(len(tokens)))
-      # only do sentences with more than 1 words excl. alpha crap
-      if len(tokens) <= 1:
-          continue
-      # Perhaps also ignore paragraphs with no sentence?
-      sentences = sent_tokenize(paragraph)
-
-      # recreate paragraph from the only words tokens list
-      paragraph = ' '.join(tokens)
-
-      print("\nParagraph:")
-      print(paragraph+"\n")
-      # T5 needs to have 'summarize' in order to work:
-      # text = "summarize:" + paragraph
-      text = paragraph
-      # encoding the input text
-      bert_legal_model(content)
-      summary = bert_legal_model(text, ratio = 0.01)
-      # summary = tokenizer_t5.decode(summary_ids[0], skip_special_tokens=True)
-      summary_text += str(summary) + "\n\n"
-      print("Summary:")
-      print(summary)
-
-  all_text =  str(summary_text) 
-
-  return all_text
+    
+    bert_legal_model(content)
+    summary = bert_legal_model(content, min_length = 8, ratio = 0.05)
+    # summary = tokenizer_t5.decode(summary_ids[0], skip_special_tokens=True)
+    summary_text += str(summary) + "\n\n"
+    print("Summary:")
+    print(summary)
+    all_text =  str(summary_text) 
+    
+    return all_text
 
     
 iface = gr.Interface(