Why faster_whisper model kills the kernel unexpectedly after running a few instances?

Question

I am trying to convert few audio data into text data using OpenAI Whisper, though the larger-model accuracy is very good but it is very slow to process the audios. But then I found faster-whisper model which solves this problem but it kills the kernel after converting few audios and exits the python program unmaturily. Don't know why is this happening even after so much tries and research. It will be great if somebody show me light on this. Machine configuration where I am running this: intel i9 14 gen processor, RTX 4090 Grpahics Card, 64 GB of RAM.

%%time
from faster_whisper import WhisperModel
audios = ["audio1.wav","audio2.wav","audio3.wav","audio4.wav","audio5.wav"]

for audio in audios:
model = WhisperModel("distil-large-v3")
segments, info = model.transcribe(audio, language="en", condition_on_previous_text=False)
for segment in segments:
    print("[%.2fs -> %.2fs] %s" %(segment.start, segment.end, segment.text))

I tried faster-whisper models to run audio conversion processes on my GPU which has Cuda 11.8. I was expecting continuous run of faster-whisper model but it is not happening.