Concept
WER
WER (Word Error Rate) is the standard accuracy metric for speech recognition, measuring how far a transcript hypothesis is from a reference. Like edit distance, except normalized by reference length and computed at the word level rather than character level.
The rest of “WER” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→