Upload config.yaml with huggingface_hub
Browse files- config.yaml +20 -0
config.yaml
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
pipeline:
|
| 2 |
+
name: pyannote.audio.pipelines.SpeakerDiarization
|
| 3 |
+
params:
|
| 4 |
+
segmentation: philschmid/pyannote-segmentation
|
| 5 |
+
segmentation_step: 0.1
|
| 6 |
+
segmentation_batch_size: 32
|
| 7 |
+
# embedding: speechbrain/spkrec-ecapa-voxceleb@5c0be3875fda05e81f3c004ed8c7c06be308de1e
|
| 8 |
+
embedding: speechbrain/spkrec-ecapa-voxceleb
|
| 9 |
+
embedding_exclude_overlap: True
|
| 10 |
+
embedding_batch_size: 32
|
| 11 |
+
clustering: HiddenMarkovModelClustering
|
| 12 |
+
|
| 13 |
+
params:
|
| 14 |
+
segmentation_onset: 0.58
|
| 15 |
+
clustering:
|
| 16 |
+
covariance_type: diag
|
| 17 |
+
threshold: 0.35
|
| 18 |
+
single_cluster_detection:
|
| 19 |
+
quantile: 0.05
|
| 20 |
+
threshold: 1.15
|