Update app.py

app.py

@@ -188,20 +188,18 @@ def chat_with_model(prompt, document_section, model_choice='Llama-2-7b-chat-hf')
                     
             except:
                 st.write('Stream llm issue')
-        SpeechSynthesis(result)
+    
+        full_reply_content = result
+        st.write("Elapsed time:")
+        st.write(time.time() - start_time)
+        
+        filename = generate_filename(full_reply_content, prompt)
+        create_file(filename, prompt, full_reply_content, should_save)
+        readitaloud(full_reply_content)
         return result
+      
     except:
         st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')
-        
-    full_reply_content = result
-    st.write("Elapsed time:")
-    st.write(time.time() - start_time)
-    
-    filename = generate_filename(full_reply_content, prompt)
-    create_file(filename, prompt, full_reply_content, should_save)
-    readitaloud(full_reply_content)
-    return result
-  
     
 # Chat and Chat with files
 def chat_with_model2(prompt, document_section, model_choice='gpt-3.5-turbo'):