SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

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 work, we analyze the impact of normalization of numerical expressions in the evaluation of ASR systems in various languages, using Polish as an example

Read original source ↗ Open in workspace

recordType

paper

region

Global