Here is a bunch of data from AWS voice transcriptions of episodes of "The Bachelor". I have some hypothesis about how language on TV is today versus where it was a long time ago when the show started and really just want to play around with this. I will keep updating the data as I have time. You'll notice that AWS isn't great in their accuracy, but they at least call it out in their data with a 'confidence' value. Example: You'll see 'Cole', 'Colleton', 'Hold it', 'Colin' and 'Cold' transcribed but they are all from "Colton