Update app.py

app.py

@@ -75,7 +75,7 @@ with demo:
     language_choices = list(language_to_models.keys())
     inputsImg=gr.Image(type='pil')
     idx=0
-    for txt in image_to_text(inputsImg)
+    for txt in image_to_text(inputsImg):
         output_txt[idx] = gr.Textbox(label=txt,lines=1,max_lines=1,value=txt,placeholder="Interpretation")
         input_sid = gr.Textbox(
                 label="Speaker ID",
@@ -96,7 +96,7 @@ with demo:
         output_audio[idx] = gr.Audio(label="Output")
         output_info[idx] = gr.HTML(label="Info")
         idx=idx+1
-    gr.Interface(fn=image_to_text, 
+    gr.Interface(fn=text_to_speech, 
                            title="Image to Text Interpretation",
                            inputs=inputsImg,
                            outputs=[output_txt,output_audio,input_sid,input_speed],