Language Identification on GlotLID-C CLD3 label set 83 languages (test)
99F1fastText
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| fastTextTraining Corpus=GlotLID-C2026.02 | 99 | 0.0079 | |
| UniLID-Mistral-NemoTokenizer=Mistral-Nemo-Base-2407, Training Corpus=GlotLID-C2026.02 | 97.2 | 0.0153 | |
| UniLIDTokenizer=UnigramLM, Training Corpus=GlotLID-C2026.02 | 97.1 | 0.0163 | |
| CLD32026.02 | 90.6 | 0.0548 |