0
votes

We are running a custom speech model use Azure's Cognitive Services / Speech-to-text and I'm running across an issue where users reported "proceed" is transcribed as "pro ceed". As it turns out, our related text has "pro ceed" in it - which explains the cause.

However, the related text was originally uploaded with the term "proceed" (not "pro ceed"). Here is a sample with just the single word:

enter image description here

The text file is UTF-8 with BOM

Has anyone else seen this?

1
Can you supply a link to the original file in which it is spelled correctly? - David Crook

1 Answers

0
votes

This is fixed and will be rolled out in the next days.