You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I would like ask if is it possible give a person a universal unique id that would be used by the model to identify him in different audio files. for ex:
There are 3 people that are talking in 2 different files. Person1 speaks first in the first file but speaks last in the second file. Can I have him be person1 in both files or is it not possible?
The text was updated successfully, but these errors were encountered:
What you are looking for is speaker verification or speaker tracking: this is feasible in pyannote.audio but does not come out of the box. See #651 and #391 for related issues.
I would like ask if is it possible give a person a universal unique id that would be used by the model to identify him in different audio files. for ex:
There are 3 people that are talking in 2 different files.
Person1 speaks first in the first file but speaks last in the second file.
Can I have him be person1 in both files or is it not possible?
The text was updated successfully, but these errors were encountered: