Hugging Face's logo

PleIAs
/
CommonLingua

Text Classification
PyTorch
multilingual
language-identification
lid
byte-level
corpus-curation
african-languages
Model card Files
xet
 Community
1
Pclanglais commited on
Commit
43fe88d
·
verified ·
1 Parent(s): 3b2902b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -46,7 +46,7 @@ We evaluated CommonLingua on CommonLID (Ortiz Suárez et al. 2026): 376 k held-o
46
  | OpenLID v2 | ~600 M | 200 | 55.77 % | 70.19 % | 0.6390 |
47
  | fastText-218 (NLLB) | ~600 M | 218 | 59.53 % | 71.64 % | 0.6590 |
48
  | GlotLID v3 | ~600 M | **2 102** | 57.69 % | 71.26 % | 0.6729 |
49
- | **CommonLingua v7.2.1** | 2.35 M | 334 | **77.63 %** | **82.92 %** | **0.7879** |
50
 
51
  CommonLingua reaches +11.5 macro F1 over the next best baseline. We discarded Lingala from our evaluation since most samples from CommonLID turned out to belong to other close languages.
52
 
 
46
  | OpenLID v2 | ~600 M | 200 | 55.77 % | 70.19 % | 0.6390 |
47
  | fastText-218 (NLLB) | ~600 M | 218 | 59.53 % | 71.64 % | 0.6590 |
48
  | GlotLID v3 | ~600 M | **2 102** | 57.69 % | 71.26 % | 0.6729 |
49
+ | **CommonLingua** | 2.35 M | 334 | **77.63 %** | **82.92 %** | **0.7879** |
50
 
51
  CommonLingua reaches +11.5 macro F1 over the next best baseline. We discarded Lingala from our evaluation since most samples from CommonLID turned out to belong to other close languages.
52