mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
75 lines
2.4 KiB
Python
75 lines
2.4 KiB
Python
import numpy as np
|
|
from pyannote.core import SlidingWindow, SlidingWindowFeature
|
|
|
|
from pyannote.audio.pipelines.clustering import AgglomerativeClustering, VBxClustering
|
|
|
|
|
|
def test_agglomerative_clustering_num_cluster():
|
|
"""
|
|
Make sure AgglomerativeClustering doesn't "over-merge" clusters when initial
|
|
clustering already matches target num_clusters, cf
|
|
https://github.com/pyannote/pyannote-audio/issues/1525
|
|
"""
|
|
|
|
# 2 embeddings different enough
|
|
embeddings = np.array([[1.0, 1.0, 1.0, 1.0], [1.0, 2.0, 1.0, 2.0]])
|
|
|
|
# clustering with params that should yield 1 cluster per embedding
|
|
clustering = AgglomerativeClustering().instantiate(
|
|
{
|
|
"method": "centroid",
|
|
"min_cluster_size": 0,
|
|
"threshold": 0.0,
|
|
}
|
|
)
|
|
|
|
# request 2 clusters
|
|
clusters = clustering.cluster(
|
|
embeddings=embeddings, min_clusters=2, max_clusters=2, num_clusters=2
|
|
)
|
|
assert np.array_equal(clusters, np.array([0, 1]))
|
|
|
|
|
|
class IdentityPLDA:
|
|
"""Minimal stand-in for PLDA (identity transform into PLDA space)"""
|
|
|
|
def __init__(self, dimension: int):
|
|
self.phi = np.ones(dimension)
|
|
|
|
def __call__(self, embeddings: np.ndarray) -> np.ndarray:
|
|
return embeddings
|
|
|
|
|
|
def test_vbx_clustering_more_clusters_than_embeddings():
|
|
"""
|
|
Make sure VBxClustering does not crash when more clusters are requested
|
|
than there are embeddings to cluster (e.g. `num_speakers` larger than
|
|
what a short file can provide) and caps the number of clusters instead.
|
|
"""
|
|
|
|
num_chunks, num_frames, num_speakers, dimension = 3, 10, 1, 4
|
|
|
|
# 3 (orthogonal) embeddings
|
|
embeddings = np.eye(dimension)[:num_chunks, np.newaxis, :]
|
|
segmentations = SlidingWindowFeature(
|
|
np.ones((num_chunks, num_frames, num_speakers)),
|
|
SlidingWindow(start=0.0, duration=10.0, step=1.0),
|
|
)
|
|
|
|
clustering = VBxClustering(plda=IdentityPLDA(dimension)).instantiate(
|
|
{"threshold": 0.6, "Fa": 0.07, "Fb": 0.8}
|
|
)
|
|
|
|
# request 5 clusters
|
|
hard_clusters, soft_clusters, centroids = clustering(
|
|
embeddings,
|
|
segmentations=segmentations,
|
|
num_clusters=5,
|
|
min_clusters=5,
|
|
max_clusters=5,
|
|
)
|
|
|
|
assert centroids.shape == (num_chunks, dimension)
|
|
assert soft_clusters.shape == (num_chunks, num_speakers, num_chunks)
|
|
assert np.array_equal(np.sort(hard_clusters.ravel()), np.arange(num_chunks))
|