🎹 说话人分割

# 1. visit hf.co/pyannote/segmentation and accept user conditions
# 2. visit hf.co/settings/tokens to create an access token
# 3. instantiate pretrained model
from pyannote.audio import Model
model = Model.from_pretrained("pyannote/segmentation", 
                              use_auth_token="ACCESS_TOKEN_GOES_HERE")

from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # onset/offset activation thresholds
  "onset": 0.5, "offset": 0.5,
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions

from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions

from pyannote.audio.pipelines import Resegmentation
pipeline = Resegmentation(segmentation=model, 
                          diarization="baseline")
pipeline.instantiate(HYPER_PARAMETERS)
resegmented_baseline = pipeline({"audio": "audio.wav", "baseline": baseline})
# where `baseline` should be provided as a pyannote.core.Annotation instance

from pyannote.audio import Inference
inference = Inference(model)
segmentation = inference("audio.wav")
# `segmentation` is a pyannote.core.SlidingWindowFeature
# instance containing raw segmentation scores like the 
# one pictured above (output)

@inproceedings{Bredin2021,
  Title = {{End-to-end speaker segmentation for overlap-aware resegmentation}},
  Author = {{Bredin}, Herv{\'e} and {Laurent}, Antoine},
  Booktitle = {Proc. Interspeech 2021},
  Address = {Brno, Czech Republic},
  Month = {August},
  Year = {2021},

@inproceedings{Bredin2020,
  Title = {{pyannote.audio: neural building blocks for speaker diarization}},
  Author = {{Bredin}, Herv{\'e} and {Yin}, Ruiqing and {Coria}, Juan Manuel and {Gelly}, Gregory and {Korshunov}, Pavel and {Lavechin}, Marvin and {Fustes}, Diego and {Titeux}, Hadrien and {Bouaziz}, Wassim and {Gill}, Marie-Philippe},
  Booktitle = {ICASSP 2020, IEEE International Conference on Acoustics, Speech, and Signal Processing},
  Address = {Barcelona, Spain},
  Month = {May},
  Year = {2020},
}