Flash Attention Support

[amrrs]

Hey! Great work.

I think the latest code change for the SpeechToTextPipeline expects all GPUs to be Flash Attention 2compatible.

I'm not sure if there's anyway to override the kwargs.

https://github.com/kadirnar/whisper-plus/blob/487bfa05572a04eb39af260eb3197533ddcdcb0d/whisperplus/pipelines/whisper.py#L72C13-L72C58

I used it on P100 from Kaggle and got the error about Flash Attention

[kadirnar]

Can you share the error message?

[kadirnar]

I added flash-attention2 as a parameter for you to turn off. You can look at Readme.