Update app.py

app.py

@@ -34,13 +34,14 @@ def generate(prompt,history,max_new_tokens,seed):
     formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
-
+    buf = ""
     for response in stream:
         if response.token.text == "\n":
-            yield from pp.stream_tts(output)
-            output=""
+            yield from pp.stream_tts(buf)
+            buf=""
+        buf += response.token.text
         output += response.token.text
-        
+        print(output)    
         #yield output
 
 with gr.Blocks() as iface: