Language Identification on FLORES-200 199 languages (test)
97.16F1GlotLID-M+ConLID-S
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GlotLID-M+ConLID-STraining Dataset=Combined/Ensemble2025.06 | 97.16 | 0.0103 | |
| GlotLID-MTraining Dataset=Subsets of GlotLID-C2025.06 | 96.96 | 0.0107 | |
| ConLID-S+LID_{CE}Training Dataset=GlotLID-C-train-down2025.06 | 96.55 | 0.0117 | |
| ConLID-STraining Dataset=GlotLID-C-train-down2025.06 | 96.52 | 0.0118 | |
| ConLID-HTraining Dataset=GlotLID-C-train-down2025.06 | 96.51 | 0.0117 | |
| LID_{CE}Training Dataset=GlotLID-C-train-down2025.06 | 96.5 | 0.0114 | |
| LID_{SCL}Training Dataset=GlotLID-C-train-down2025.06 | 96.17 | 0.0118 |