The Hidden Cost of Digits: Number Normalization and WER in ASR Systems

Excerpt

arXiv:2609.21084v1 Announce Type: cross Abstract: Modern automatic speech recognition (ASR) systems trained on extremely large datasets can produce transcripts with numbers written in Arabic numerals. This creates a need for fair comparison with models that output verbatim texts and proper processing of reference transcripts. Popular approaches often reduce text normalization to lowercase and remove punctuation, with no additional normalization applied to languages other than English. In this wo