Update app.py

app.py

@@ -48,15 +48,26 @@ def generateAudio(text_to_audio, s3_save_as):
     
     s3_save_as = '-'.join(s3_save_as.split()) + ".wav"
     
-    def cut_text(text, max_tokens=500):
+   def cut_text(text, max_tokens=500):
         # Remove non-alphanumeric characters, except periods and commas
         text = re.sub(r"[^\w\s.,]", "", text)
-        
-        tokens = word_tokenize(text)
+    
+        # Replace multiple spaces with a single space
+        text = re.sub(r"\s{2,}", " ", text)
+    
+        # Remove line breaks
+        text = re.sub(r"\n", " ", text)
+    
+        sentences = sent_tokenize(text)
+        tokens = []
+        for sentence in sentences:
+            tokens.extend(word_tokenize(sentence))
+    
         if len(tokens) <= max_tokens:
             return text
-        
-        cut = ' '.join(tokens[:max_tokens])
+    
+        cut_tokens = tokens[:max_tokens]
+        cut = ' '.join(cut_tokens)
         return cut
 
     def save_audio_to_s3(audio):