nparray as pipeline input.

[sense2k8]

Hi,
how to use ndarray from soundfile to pipeline. Example says Pipeline takes only audio file.

from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained("pyannote/overlapped-speech-detection")
output = pipeline("audio.wav") <-------------------- Want to replace this with below code snippet

import soundfile as sf
waveform, sr = sf.read('sample.wav')
output = pipeline(waveform)

[hbredin]

See this tutorial, section "Processing a file from memory".