added stated line

app.py

@@ -86,12 +86,12 @@ def parse_transcription(wav_file):
 
     # generate image
     image = generate_image(translated)
-    return image 
+    return transcription, image 
 
-output = gr.outputs.Image(label='')
+outputs = [gr.outputs.Textbox(label="transcript"), gr.outputs.Image(label='')]
 input_mic = gr.inputs.Audio(source="microphone", type="file", optional=True)
 
-gr.Interface(parse_transcription, inputs=[input_mic],  outputs=output,
+gr.Interface(parse_transcription, inputs=[input_mic],  outputs=outputs,
              analytics_enabled=False,
              show_tips=False,
              theme='huggingface',