Spaces:

ConvxO2
/

Who-Spoke-When

Running

App Files Files Community

Who-Spoke-When / models

10.6 kB

1 contributor

History: 8 commits

ConvxO2's picture

Reduce speaker over-segmentation in auto clustering

789006e 6 days ago

__init__.py

0 Bytes

Initial commit: Speaker Diarization System 13 days ago
clusterer.py

4.5 kB

Reduce speaker over-segmentation in auto clustering 6 days ago
embedder.py

6.13 kB

Fix stereo duration handling and robust ECAPA model loading 7 days ago