Inconsistent transcriptions?

[RikRaesTNO]

When using whisper (currently only the tiny version), I obtain different transcriptions every time I run them. I use the transcription using the code outlined below. Can anyone explain this or help me obtain consistent transcriptions?

import whisper
model = whisper.load_model("tiny")
result = model.transcribe(audio)
text = result["text"]

[phineas-pta]

it's the default behaviour see #81