Update app.py

app.py

@@ -19,6 +19,12 @@ for root, dirs, files in os.walk(local_dir):
         print(file_path)
 
 result_dir = "results"
+def set_upload():
+    return "upload"
+def set_microphone():
+    return "microphone"
+def set_tts():
+    return "tts"
 
 @spaces.GPU
 def predict(prompt, upload_reference_audio, microphone_reference_audio, reference_audio_type):
@@ -69,14 +75,14 @@ def main():
                 with gr.Tabs(elem_id="kdtalker_driven_audio"):
                     with gr.TabItem("Upload"):
                         upload_driven_audio = gr.Audio(label="Upload audio", sources="upload", type="filepath")
-                        upload_driven_audio.change(lambda: "upload", outputs=driven_audio_type)
+                        upload_driven_audio.change(set_upload, outputs=driven_audio_type)
                     reference_audio_type = gr.State(value="upload")
 
                     with gr.TabItem("TTS"):
                         upload_reference_audio = gr.Audio(label="Upload Reference Audio", sources="upload", type="filepath")
-                        upload_reference_audio.change(lambda: "upload", outputs=reference_audio_type)
+                        upload_reference_audio.change(set_upload, outputs=reference_audio_type)
                         microphone_reference_audio = gr.Audio(label="Recorded Reference Audio", sources="microphone", type="filepath")
-                        microphone_reference_audio.change(lambda: "microphone", outputs=reference_audio_type)
+                        microphone_reference_audio.change(set_microphone, outputs=reference_audio_type)
                         input_text = gr.Textbox(
                             label="Generating audio from text",
                             lines=5,
@@ -85,7 +91,7 @@ def main():
                         tts_button = gr.Button("Generate audio", elem_id="kdtalker_audio_generate", variant="primary")
                         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(lambda: "tts", outputs=driven_audio_type)
+                        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)