Detects the language of a text among 183 languages with language-detection-small (141M, Apache-2.0), running entirely in your browser. The first run downloads the model, which is then cached. Results update as you type.
Loading model…
Labels are ISO 639-3 language + script codes (FLORES-200). Close varieties (e.g. Bosnian/Croatian) are often confused; Arabic dialects are reported as
arb_Arab, and very short inputs are less reliable. See the model card for measured accuracy.