Add code

app.py

@@ -107,7 +107,7 @@ def determine_pause(audio: np.ndarray, sampling_rate: int, state: AppState) -> b
 
     print(f"duration_after_vad: {dur_vad:.3f} s, time_vad: {time_vad:.3f} s")
 
-    return (duration - dur_vad) > 0.5
+    return (duration - dur_vad) > 1
 
 
 def speaking(audio: np.ndarray, sampling_rate: int):
@@ -180,6 +180,11 @@ def response(state: AppState):
     yield None, AppState()
 
 
+def start_recording_user(state: AppState):
+    if state.pause_detected and state.started_talking:
+        return gr.Audio(recording=True)
+    return None
+
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
@@ -202,13 +207,13 @@ with gr.Blocks() as demo:
         [state],
         [output_audio, state]
     )
-    output_audio.stop(
-        lambda: gr.Audio(recording=True),
-        None,
+    restart = output_audio.stop(
+        start_recording_user,
+        [state],
         [input_audio]
     )
     cancel = gr.Button("Stop Conversation", variant="stop")
-    cancel.click(lambda: AppState(), None, [state], cancels=[respond])
+    cancel.click(lambda: AppState(), None, [state], cancels=[respond, restart])
 
 
 demo.launch()