Here is my so far code

# SETUP
from pydub import AudioSegment
import torch
pipeline.to(torch.device("cuda"))

from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained(
    "pyannote/speaker-diarization-3.1",
    use_auth_token="hf_#####")



audio = AudioSegment.from_file(file_path)

# DO SOMETHING

audio.export("temp_file.wav", format="wav") # I want to skip this line

diarization = pipeline("temp_file.wav")

I want to skip the part exporrt it to a temp file then have the Pipeline process it, so I dont need to borther removing the temp file