I went through some files (audioAnalysis.py, audioSegmentation.py) and as far i understand diarization feature is implemented only for more than 1 speaker (basically this is implemented assuming # of speakers in an audio as between 2 and 9 when # of speakers are unknown). In my case, I have audio files that may contain only a single speaker. To modify the code and get it work, I could not understand the implementation very well. Can someone help me regarding this?
I went through some files (audioAnalysis.py, audioSegmentation.py) and as far i understand diarization feature is implemented only for more than 1 speaker (basically this is implemented assuming # of speakers in an audio as between 2 and 9 when # of speakers are unknown). In my case, I have audio files that may contain only a single speaker. To modify the code and get it work, I could not understand the implementation very well. Can someone help me regarding this?