Update app.py

app.py

@@ -258,6 +258,7 @@ def txt2speech(text):
 def main(audio_filepath, src_lang, tgt_lang, pnc):
     translated = transcribe(audio_filepath, src_lang, tgt_lang, pnc)
     answer = llm_pipe(translated, **generation_args)
+    txt2speech(answer[0]['generated_text'])
     # return [answer[0]['generated_text'], 'audio_out.mp3']
     return 'audio_out.mp3'
     
@@ -313,7 +314,7 @@ with gr.Blocks(
 				variant="primary", # make "primary" so it stands out (default is "secondary")
 			)
 
-            audio_out = gr.Audio(label="Generated Audio", type="numpy", elem_id="audio_out")
+            audio_out = gr.Audio(label="Generated Audio", type="filepath", elem_id="audio_out", interactive=False)
 
 			# model_output_text_box = gr.Textbox(
 			# 	label="Model Output",