Update app.py

app.py

@@ -39,16 +39,14 @@ def one_shot(image,input_text,gender):
      image = Image.open(image_in)
      image = pad_image(image)
      image.save("/content/image_pre.png")
-     print("Print 2")
-     return  "/content/image_pre.png"
-     exit()
      pocketsphinx_run = subprocess.run(['pocketsphinx', '-phone_align', 'yes', 'single', '/content/audio.wav'], check=True, capture_output=True)
      jq_run = subprocess.run(['jq', '[.w[]|{word: (.t | ascii_upcase | sub("<S>"; "sil") | sub("<SIL>"; "sil") | sub("\\\(2\\\)"; "") | sub("\\\(3\\\)"; "") | sub("\\\(4\\\)"; "") | sub("\\\[SPEECH\\\]"; "SIL") | sub("\\\[NOISE\\\]"; "SIL")), phones: [.w[]|{ph: .t | sub("\\\+SPN\\\+"; "SIL") | sub("\\\+NSN\\\+"; "SIL"), bg: (.b*100)|floor, ed: (.b*100+.d*100)|floor}]}]'], input=pocketsphinx_run.stdout, capture_output=True)
      with open("test.json", "w") as f:
          f.write(jq_run.stdout.decode('utf-8').strip())
     
      os.system(f"cd /content/one-shot-talking-face && python3 -B test_script.py --img_path /content/image_pre.png --audio_path /content/audio.wav --phoneme_path /content/test.json --save_dir /content/train")
-    
+     return "/content/train/image_pre_audio.mp4"
+     exit()
       #1. Extract the frames from the video file using PyVideoFramesExtractor
      os.system(f"python /content/PyVideoFramesExtractor/extract.py --video=/content/train/image_pre_audio.mp4")
     
@@ -103,7 +101,7 @@ def run():
           # audio_in = gr.Audio(show_label=False, type='filepath')
           input_text=gr.Textbox(lines=3, value="Hello How are you?", label="Input Text")
           gender = gr.Radio(["Female","Male"],value="Female",label="Gender")
-          video_out = gr.Image(label="output")
+          video_out = gr.Video(label="output")
           # video_out = gr.Video(show_label=False)
         with gr.Row().style(equal_height=True):
           btn = gr.Button("Generate")