File size: 601 Bytes
475d28a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
pipeline:
  name: pyannote.audio.pipelines.SpeakerDiarization
  params:
    segmentation: philschmid/pyannote-segmentation
    segmentation_step: 0.1
    segmentation_batch_size: 32
    # embedding: speechbrain/spkrec-ecapa-voxceleb@5c0be3875fda05e81f3c004ed8c7c06be308de1e
    embedding: speechbrain/spkrec-ecapa-voxceleb
    embedding_exclude_overlap: True
    embedding_batch_size: 32
    clustering: HiddenMarkovModelClustering

params:
  segmentation_onset: 0.58
  clustering:
    covariance_type: diag
    threshold: 0.35
    single_cluster_detection:
      quantile: 0.05
      threshold: 1.15