After upgrading from 1.34.0 to 1.40.0, we noticed that the speech diarization's quality has worsened significantly and it only started picking up 2 speakers
I found this document for the batch transcriber indicating that the number of speakers is limited to two by default and it shows parameters to set minCount and maxCount, what is the equivalent for this in the speech SDK?
Please note we're performing real time speech diarization and would like to upgrade to the latest version for performance issues.
Version
1.40.0 (Latest)
What browser/platform are you seeing the problem on?
What happened?
After upgrading from
1.34.0to1.40.0, we noticed that the speech diarization's quality has worsened significantly and it only started picking up 2 speakers I found this document for the batch transcriber indicating that the number of speakers is limited to two by default and it shows parameters to setminCountandmaxCount, what is the equivalent for this in the speech SDK? Please note we're performing real time speech diarization and would like to upgrade to the latest version for performance issues.Version
1.40.0 (Latest)
What browser/platform are you seeing the problem on?
Node
Relevant log output