Update utils.py

utils.py

@@ -24,7 +24,8 @@ import nltk
 nltk.download('punkt')
 nltk.download('averaged_perceptron_tagger')
 from nltk.tokenize import sent_tokenize
-import re
+import re 
+import stanfordnlp
 def welcome():
     return "Welcome All"
 
@@ -84,4 +85,14 @@ def get_translation(source, dest, text):
         translation = translator.translate(i)
         trans.append(translation)
     
-    return ' '.join(trans)
+    return ' '.join(trans)
+    
+
+def truecasing_by_sentence_segmentation(input_text):
+    # split the text into sentences
+    sentences = sent_tokenize(input_text, language='english')
+    # capitalize the sentences
+    sentences_capitalized = [s.capitalize() for s in sentences]
+    # join the capitalized sentences
+    text_truecase = re.sub(" (?=[\.,'!?:;])", "", ' '.join(sentences_capitalized))
+    return text_truecase