AfriCOMET

AfriCOMET is a COMET-based machine translation evaluation model for African languages, scoring translation quality from source, hypothesis and reference triplets. The STL-1.1 version uses the afro-xlmr-large-76L encoder and was validated in the WMT 2024 Metrics Shared Task across 13 African-centric language pairs. It is released by the Masakhane community with reference-based and quality-estimation variants.

Category

AI Resources

Pricing

Open weights (Apache 2.0)

Country

🌍 Pan-African

Last verified

10 Oct 2026

{
  "name": "AfriCOMET",
  "slug": "africomet",
  "category": "AI",
  "country": "Pan-African",
  "docs_status": "LIVE",
  "licensing_required": "NONE",
  "verified": false,
  "last_verified": "2026-10-10",
  "website": "https://huggingface.co/masakhane/africomet-stl-1.1",
  "documentation_url": "https://github.com/masakhane-io/africomet"
}