Language Identification on FLORES-200 Full (190 labels) (test)
96.8F1 ScoreGlotLID-M
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GlotLID-MArchitecture=fastText, Training Corpus=GlotLID-C2026.02 | 96.8 | 0.0135 | |
| fastTextTraining Corpus=GlotLID-C2026.02 | 93.8 | 0.0238 | |
| UniLIDTokenizer=UnigramLM, Training Corpus=GlotLID-C2026.02 | 93.2 | 0.0278 | |
| UniLID-Mistral-NemoTokenizer=Mistral-Nemo-Base-2407, Training Corpus=GlotLID-C2026.02 | 92.3 | 0.0322 |