lower text..

app.py

@@ -25,7 +25,7 @@ def speech2text(audio):
     predicted_ids = torch.argmax(logits, dim=-1)
     transcription = processor.batch_decode(predicted_ids)
 
-    return transcription[0]  # batch size 1
+    return transcription[0].lower()  # batch size 1
 
 iface = gr.Interface(speech2text, "microphone", "text")