Update app.py

app.py

@@ -391,16 +391,16 @@ with gr.Blocks(title="BLIP Vision App") as demo:
         btn1.click(generate_caption_translate_speak, inputs=[img_in, lang_in], outputs=[eng_out, trans_out, audio_out])
 
     with gr.Tab("Voice Question Answering"):
-    img_vqa = gr.Image(type="pil", label="Upload Image for Voice Q&A")
-    voice_in = gr.Audio(source="microphone", type="filepath", label="Speak your question")
-    voice_out_text = gr.Textbox(label="Voice Q&A Output")
-    voice_out_audio = gr.Audio(label="Spoken Answer", type="filepath")
-    btn_voice = gr.Button("Get Answer")
-    btn_voice.click(
-        voice_question_answer, 
-        inputs=[img_vqa, voice_in], 
-        outputs=[voice_out_text, voice_out_audio]
-    )
+        img_vqa = gr.Image(type="pil", label="Upload Image for Voice Q&A")
+        voice_in = gr.Audio(source="microphone", type="filepath", label="Speak your question")
+        voice_out_text = gr.Textbox(label="Voice Q&A Output")
+        voice_out_audio = gr.Audio(label="Spoken Answer", type="filepath")
+        btn_voice = gr.Button("Get Answer")
+        btn_voice.click(
+            voice_question_answer, 
+            inputs=[img_vqa, voice_in], 
+            outputs=[voice_out_text, voice_out_audio]
+        )
 
 
     with gr.Tab("Text VQA (Optional)"):