Kernel crash in Juptyer notebook while processing lengthy audio.

[manjunath7472]

Hi there, My Specs RTX 4000 - 8GB Cuda 11.8 - Cudnn 8.9.1 32GB Ram model used- large v2 - float 16 input audio length: 45 min

When audio Input length is more than 30 min kernal crashing. tried medium.en with int8 compute. Still same issue. Even process stopping in normal run too.

[MahmoudAshraf97]

in which step does it crash?

[manjunath7472]

In transcribe cell, we need to remove below lines to avoid kernel crash while transcribing. It also solves problem where all dialogues are stuffed under one speaker.

del whisper_model torch.cuda.empty_cache()