Update app.py

app.py

@@ -155,7 +155,7 @@ def one_shot_talking(image_in,audio_in):
   torchaudio.save("/content/audio.wav", waveform, sample_rate, encoding="PCM_S", bits_per_sample=16)
   image = Image.open(image_in)
   image = pad_image(image)
-  image.save("image_pre.png")
+  image.save("/content/image_pre.png")
 
   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)