BACK
WER (Word Error Rate)
A standard metric for transcription accuracy; the share of words transcribed incorrectly, where lower is better.
Word Error Rate (WER) is the standard metric for measuring the accuracy of speech recognition and transcription, calculated from the proportion of words inserted, deleted, or substituted compared to a correct reference. A lower WER means more accurate transcription. Because background music and noise drive WER up, isolating a clean speech or dialogue stem before transcription is a reliable way to reduce it.
Related terms
Where this comes up at AudioShake