Speaker diarization is just one option for identifying individuals talking. Another option is to record separate channels for each speaker. Then, each channel tag will represent a unique individual.

A standard use case would be a phone call recording where each person’s audio is captured on a separate track. This kind of thing is fairly common in modern IVR (Interactive Voice Response) systems or call center audio capture.

A very small change to the code below can be made to call out the idea that each channel is a different speaker.

You can also receive help from the hints given below.