Update app.py

app.py

@@ -156,7 +156,8 @@ def one_shot_talking(image_in,audio_in):
   image = Image.open(image_in)
   image = pad_image(image)
   image.save("/content/image_pre.png")
-
+  return "/content/audio.wav"
+  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:
@@ -164,7 +165,7 @@ def one_shot_talking(image_in,audio_in):
 
   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")
 
-  
+  exit()
   #Video Quality Improvement
 
   #1. Extract the frames from the video file using PyVideoFramesExtractor