No. Separate tracks are created by separate audio inputs, i.e. the separate devices each person is recording on. Since the transcript is generated based on the available tracks, the transcript cannot differentiate between two people using one microphone.
To distinguish between speakers on the transcript, use a separate microphone for each participant.
However, if you do have a recording where multiple people are speaking on the same track, you can export the recording and then re-upload it to Riverside and select multiple speakers. This will create separate audio tracks for each speaker that you can then rename in the editor.