← All data sources← All Language Processing observatories on IDLI

data source

fastText LID (NLLB)

Open fastText LID (NLLB)

217 FLORES-200 labels from Meta's NLLB language-identification model.

language-id
Languages identifiable
211
Total script labels
218

Languages in fastText LID (NLLB)

40 of 211 shown

Detail
Abkhazian
abk
1detail →
Armenian
hye
1detail →
Asturian
ast
1detail →
Belarusian
bel
1detail →
Bosnian
bos
1detail →
Bulgarian
bul
1detail →
Croatian
hrv
1detail →
Estonian
est
1detail →
Fijian
fij
1detail →
Friulian
fur
1detail →
Galician
glg
1detail →
Georgian
kat
1detail →
Haitian
hat
1detail →
Halh Mongolian
khk
1detail →
Hungarian
hun
1detail →
Indonesian
ind
1detail →
Iranian Persian
pes
1detail →
Italian
ita
1detail →
Kabuverdianu
kea
1detail →
Latgalian
ltg
1detail →
Ligurian
lij
1detail →
Lithuanian
lit
1detail →
Macedonian
mkd
1detail →
Mingrelian
xmf
1detail →
Nigerian Fulfulde
fuv
1detail →
Nigerian Pidgin
pcm
1detail →
Norwegian Bokmål
nob
1detail →
Norwegian Nynorsk
nno
1detail →
Romanian
ron
1detail →
Russian
rus
1detail →
Sardinian
srd
1detail →
Serbian
srp
1detail →
Sicilian
scn
1detail →
Silesian
szl
1detail →
Slovenian
slv
1detail →
Standard Latvian
lvs
1detail →
Tahitian
tah
1detail →
Tosk Albanian
als
1detail →
Ukrainian
ukr
1detail →
Venetian
vec
1detail →

Community portal

Opportunities, events, and experts across the digital language inclusion ecosystem.