Duplicated from philschmid/pyannote-speaker-diarization-endpoint
How to use BoKnows/vad-endpoint with pyannote.audio:
from pyannote.audio import Pipeline pipeline = Pipeline.from_pretrained("BoKnows/vad-endpoint") # inference on the whole file pipeline("file.wav") # inference on an excerpt from pyannote.core import Segment excerpt = Segment(start=2.0, end=5.0) from pyannote.audio import Audio waveform, sample_rate = Audio().crop("file.wav", excerpt) pipeline({"waveform": waveform, "sample_rate": sample_rate})
