add tqdm gradio tracking

gradio_app.py

@@ -378,7 +378,7 @@ class Inferencer(object):
         os.remove(new_audio_path)
 
 @spaces.GPU()
-def gradio_infer(source_image, driven_audio):
+def gradio_infer(source_image, driven_audio, progress=gr.Progress(track_tqdm=True)):
     """
     Generate a talking-head video from a static source image and an audio file.