Why is speaker identification for AWS Transcribe no longer working?

I have noticed that speaker identification for AWS transcribe is off by few seconds. s3://speechrealtime/medical-diarization.wav

Here is the result for the file above (With asterisks added ): Speaker 0: Hey jane. So what brings you into my office today?Hey, dr Michaels, Good to see you. I'm just coming in from my***

Speaker 1: routine checkup.*** Alright, let's see. I last saw you about what? Like a year ago and at that time I think you were having some minor headaches.I don't recall prescribing***

Speaker 0: anything and we said we'd maintain some observations unless things were getting worse.***That's right. ***Actually the headaches have gone away. I think getting more sleep was super helpful. I've also been more careful about my water intake throughout my workday.***Yeah, I'm not surprised at all. Sleep deprivation and chronic dehydration are two common contributors to potential headaches. Rest is definitely vital when you become dehydrated? Also your brain tissue loses

Speaker 1: water causing your brain to shrink and you know, kind of pull away from the skull and this can trigger the pain receptors around the brain giving you the sensation of a headache.So how much water are you roughly taking in in each dayof? ***Um I've become obsessed with drinking enough water. I have one of those fancy water bottles that have graduated

Speaker 0: markers on the side.I've also been logging my water intake pretty regularly on average. I drink about 3l a day. ***That's excellent. Before I start a routine physical exam, is there anything else you'd like me to know anything you'd like to share? What else has been bothering you

Speaker differeentiation is constatnly off by few seconds. I just wanted to bring this to your attention.