Update app.py

app.py

@@ -74,6 +74,7 @@ def main():
         """
         )
         driven_audio_type = gr.Textbox(value="upload", visible=False) 
+        reference_audio_type = gr.Textbox(value="upload", visible=False)
 
         with gr.Row():
             with gr.Column(variant="panel"):
@@ -85,8 +86,6 @@ def main():
                     with gr.TabItem("Upload"):
                         upload_driven_audio = gr.Audio(label="Upload audio", sources="upload", type="filepath")
                         upload_driven_audio.change(set_upload, outputs=driven_audio_type)
-                    reference_audio_type = gr.Textbox(value="upload", visible=False)
-
                     with gr.TabItem("TTS"):
                         upload_reference_audio = gr.Audio(label="Upload Reference Audio", sources="upload", type="filepath")
                         upload_reference_audio.change(set_upload, outputs=reference_audio_type)
@@ -101,7 +100,6 @@ def main():
                         tts_driven_audio = gr.Audio(label="Synthesised Audio", type="filepath")
                         tts_button.click(fn=predict, inputs=[input_text, upload_reference_audio, microphone_reference_audio, reference_audio_type], outputs=[tts_driven_audio])
                         tts_button.click(set_tts, outputs=driven_audio_type)
-
             with gr.Column(variant="panel"):
                 gen_video = gr.Video(label="Generated video", format="mp4", width=256)
                 with gr.Tabs(elem_id="talker_checkbox"):