Fact · Speech recognition
Vosk says its big models have a fixed vocabulary that cannot be changed while the model runs.
Checked against its source on October 17, 2026
In the source's own words
“Big models are static the vocabulary can not be modified in runtime.”
Vosk models (Alpha Cephei), Alpha Cephei, 2026, Models section, first paragraph.
Open the original- What it measures
- Vosk contrasts its big models with its small ones, which it says suit limited tasks on mobile applications.
- What it does not show
- Applies to the big models named in the project's guidance. It does not describe the small models, which the project presents as suited to limited tasks.