# 1. visit hf.co/pyannote/embedding 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/embedding", 
                              use_auth_token="ACCESS_TOKEN_GOES_HERE")

python

from pyannote.audio import Inference
inference = Inference(model, window="whole")
embedding1 = inference("speaker1.wav")
embedding2 = inference("speaker2.wav")
# `embeddingX` is (1 x D) numpy array extracted from the file as a whole.

from scipy.spatial.distance import cdist
distance = cdist(embedding1, embedding2, metric="cosine")[0,0]
# `distance` is a `float` describing how dissimilar speakers 1 and 2 are.

Using cosine distance directly, this model reaches 2.8% equal error rate (EER) on VoxCeleb 1 test set.
This is without voice activity detection (VAD) nor probabilistic linear discriminant analysis (PLDA). Expect even better results when adding one of those.

Advanced usage

Running on GPU

python

import torch
inference.to(torch.device("cuda"))
embedding = inference("audio.wav")

Extract embedding from an excerpt

python

from pyannote.audio import Inference
from pyannote.core import Segment
inference = Inference(model, window="whole")
excerpt = Segment(13.37, 19.81)
embedding = inference.crop("audio.wav", excerpt)
# `embedding` is (1 x D) numpy array extracted from the file excerpt.

Extract embeddings using a sliding window

python

from pyannote.audio import Inference
inference = Inference(model, window="sliding",
                      duration=3.0, step=1.0)
embeddings = inference("audio.wav")
# `embeddings` is a (N x D) pyannote.core.SlidingWindowFeature
# `embeddings[i]` is the embedding of the ith position of the 
# sliding window, i.e. from [i * step, i * step + duration].

Citation

bibtex

@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},
}

bibtex

@inproceedings{Coria2020,
    author="Coria, Juan M. and Bredin, Herv{\'e} and Ghannay, Sahar and Rosset, Sophie",
    editor="Espinosa-Anke, Luis and Mart{\'i}n-Vide, Carlos and Spasi{\'{c}}, Irena",
    title="{A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification}",
    booktitle="Statistical Language and Speech Processing",
    year="2020",
    publisher="Springer International Publishing",
    pages="137--148",
    isbn="978-3-030-59430-5"
}

Mirror provenance

This repository is an unmodified copy of pyannote/embedding at commit 4db4899737a38b2d618bbd74350915aa10293cb2, mirrored on 2026-08-12 so that it can be fetched without the upstream access form. No weights, configuration or licence terms were changed; all credit and the original licence remain with the upstream authors.

lovehunter9/pyannote-embedding

🎹 Speaker embedding

Basic usage

Advanced usage

Running on GPU

Extract embedding from an excerpt

Extract embeddings using a sliding window

Citation

Mirror provenance

lovehunter9/
pyannote-embedding