small fixes

app.py

@@ -2,7 +2,6 @@ import soundfile as sf
 import gradio as gr
 import jax
 import numpy as np
-import os
 from PIL import Image
 import random
 import sox
@@ -87,9 +86,9 @@ def parse_transcription(wav_file):
 
     # generate image
     image = generate_image(translated)
-    return transcription, image 
+    return transcription, translated, image 
 
-outputs = [gr.outputs.Textbox(label="transcript"), gr.outputs.Image(label='')]
+outputs = [gr.outputs.Textbox(label="transcript"), gr.outputs.Textbox(label="translated prompet"), gr.outputs.Image(label='')]
 input_mic = gr.inputs.Audio(source="microphone", type="file", optional=True)
 
 gr.Interface(parse_transcription, inputs=[input_mic],  outputs=outputs,