finish

app.py

@@ -32,17 +32,19 @@ def transcribe(url):
 
     output = pipe(speech_array)
 
-    return output["text"]
+    return "audio.mp3", output["text"], "latest_titanic.png"
 
 
 iface = gr.Interface(
     fn=transcribe,
     inputs=gr.Textbox("https://www.youtube.com/watch?v=n9g12Xm9UJM", label="Paste a YouTube video URL"),
-    outputs=[gr.Textbox(label="Transcription")],
+    outputs=[gr.Audio(label="Transcripted Audio"),
+             gr.Textbox(label="Transcription"),
+             gr.Image(label="Model Scores")
+],
     title="Whisper Small Swedish",
     description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
     allow_flagging="never"
 )
 
 iface.launch()
-#              gr.Image("latest_titanic.png", label="Model Scores")