Fact · Speech recognition
14.1percent word error rate
On a subset of Google's voice search task, the LAS model reached a word error rate of 14.1 percent without a dictionary or a language model.
Checked against its source on October 17, 2026
In the source's own words
“On a subset of the Google voice search task, LAS achieves a word error rate (WER) of 14.1% without a dictionary or a language model”
Listen, Attend and Spell, William Chan et al., arXiv, 2015, Abstract.
Open the original- What it measures
- This is the model without any external language model. The same paper reports a lower figure when a language model rescores its output, which is the usual practice in production systems of the time.
- What it does not show
- A subset of voice search queries, which are short, so the number does not describe long dictation. The arXiv versions report different figures, so check the version you cite.