alt Hacker NewsOh wow, I thought humans are like 0.1% error rate, if they are native speakers and aware of the subject being discussed.
Replies
rhdunn • today at 8:51 PM
It can depend a lot on different factors like:
- familiarity with the accent and/or speaker;
- speed and style/cadence of the speech;
- any other audio that is happening that can muffle or distort the audio;
- etc.
It can also take multiple passes to get a decent transcription.
➕ show 1 reply
Nimitz14 • today at 9:17 PM
Most of these errors will not be meaningful. Real speech is full of ambiguities. 3% is low
I was skepitcal upon hearing the figure but various sources do indeed back it up and [0] is a pretty interesting paper (old but still relevant human transcibers haven't changed in accuracy).
[0] https://www.microsoft.com/en-us/research/wp-content/uploads/...