Language Identification on UDHR CLD3 label set 80 languages (test)
0.998F1 ScorefastText
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| fastTextTraining Corpus=GlotLID-C2026.02 | 0.998 | 0 | |
| GlotLID-MArchitecture=fastText, Training Corpus=GlotLID-C2026.02 | 0.994 | 0 | |
| UniLIDTokenizer=UnigramLM, Training Corpus=GlotLID-C2026.02 | 0.992 | 0 | |
| UniLID-Mistral-NemoTokenizer=Mistral-Nemo-Base-2407, Training Corpus=GlotLID-C2026.02 | 0.992 | 0.0001 | |
| CLD32026.02 | 0.965 | 0.0003 |