Update app.py

app.py

@@ -35,31 +35,27 @@ def one_shot(image,input_text,gender):
           sound.export("/content/audio.wav", format="wav")
      waveform, sample_rate = torchaudio.load("/content/audio.wav")
 
-     try:
-         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("/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)
-         with open("test.json", "w") as f:
-             f.write(jq_run.stdout.decode('utf-8').strip())
-         import json
-
-         with open('test.json') as user_file:
-           file_contents = user_file.read()
-          
-         
-        
-         parsed_json = json.loads(file_contents)
-         return parsed_json
-         exit()
-         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")
-         
-     except Exception as e:
-         print(e)
+     
+     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("/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)
+     with open("test.json", "w") as f:
+         f.write(jq_run.stdout.decode('utf-8').strip())
+     import json
+
+     with open('test.json') as user_file:
+       file_contents = user_file.read()
+      
+     
+    
+     parsed_json = json.loads(file_contents)
      return parsed_json
      exit()
+     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")
+