Geographic & Linguistic Coverage

One platform for the Maghreb — in production in Tunisia, available on request in Algeria, Morocco and Libya.

4 Countries, 8 Languages, 21 Dialect Zones

4 Countries, 8 Languages, 21 Dialect Zones
Tunisia — in productionAlgeria · Morocco · Libya — on request
TN

Tunisia

Regions24 Gouvernorates
Dialect Zones6
Languages1
Tunisian Derja (ar-TN)
DZ

Algeria

Regions58 Wilayas
Dialect Zones6
Languages2
Algerian Darja (ar-DZ)
Kabyle (kab)
LY

Libya

Regions22 Shabiyat
Dialect Zones4
Languages1
Libyan Arabic (ar-LY)
MA

Morocco

Regions12 Regions
Dialect Zones5
Languages4
Moroccan Darija (ar-MA)
Tashelhit (shi)
Tarifit (rif)
Central Atlas Tamazight (tzm)

Supported Languages & Scripts

LanguageScriptCountryStatus
Tunisian Derja(ar-TN)Arabic + ArabiziTunisiaActive
Algerian Darja(ar-DZ)ArabicAlgeriaOn request
Libyan Arabic(ar-LY)ArabicLibyaOn request
Moroccan Darija(ar-MA)ArabicMoroccoOn request
Kabyle(kab)Latin + TifinaghAlgeriaOn request
Central Atlas Tamazight(tzm)Tifinagh + LatinMoroccoOn request
Tashelhit(shi)Tifinagh + LatinMoroccoOn request
Tarifit(rif)Latin + TifinaghMoroccoOn request

The Arabizi System

North Africans routinely write their dialects in Latin script, using numerals for Arabic sounds. This dual-script reality is precisely what our transliteration datasets capture.

3579
9ahwa bel 7lib=قهوة بالحليب(coffee with milk)
Hands typing a message on a phone beside handwritten notes in Latin letters and numerals

Tell us what you need to train.

Language, domain, volume — we reply with availability, a sample dataset and a quote. Custom collection typically begins within weeks.