Update app.py

app.py

@@ -43,7 +43,7 @@ def calculate(image_in, audio_in):
     image = Image.open(image_in)
     image = pad_image(image)
     image.save("image.png")
-    return image
+    return audio_in
     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:
@@ -104,7 +104,7 @@ 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.Audio(label="output")
           # video_out = gr.Video(show_label=False)
         with gr.Row().style(equal_height=True):
           btn = gr.Button("Generate")