Replies: 1 comment
-
I did not expose this You can definitely try that though (and report back 🙏) but it would need a bit of work on your side to edit the code. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
In the diarization pipeline is the following parameter:
segmentation_step: float, optional The segmentation model is applied on a window sliding over the whole audio file. "segmentation_step" controls the step of this window, provided as a ratio of its duration. Defaults to 0.1 (i.e. 90% overlap between two consecuive windows).
Now changing this ratio speeds up the diarization process significantly (and without much loss of accuracy). Since the segmentation step is a ratio of the duration of the window. Is it also possible to extend the window length? I would like to experiment with longer window lengths to check the results compared with processing speed. Thanks!
Beta Was this translation helpful? Give feedback.
All reactions