Torch warning when using mb-roformer (Faster-Whisper-XXL Pro)

[bbqrooster]

When I run the Faster-Whisper-XXL Pro using the mb-roformer model, I got the warning message

"faster_whisper\roformer_attend.py:73: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263."

The command that I used was ""%dp%faster-whisper-xxl.exe" %file_list% -pp -o source --batch_recursive --check_files --standard -f srt -l Japanese -m large-v2 -o source --temperature 0 --word_timestamps True --ff_vocal_extract mb-roformer --vad_method pyannote_v3".

Although this warning occurred didn't matter what vad_method I used.

Is this an issue needed to be fixed? What do I need to do to correct it?

[Purfview]

Is this an issue needed to be fixed?

It's just a warning, nothing to worry about, produced because torch doesn't support flash attention on Windows.
I'll hide it in the next version.

[libero08]

import warnings
warnings.filterwarnings("ignore", message="Torch was not compiled with flash attention")
more easyest way to hide untill next version :)

Start into a hybrid way.