Open models
Research-preview weights on Hugging Face. Small models for African languages and edge settings, starting with Swahili→Sukuma machine translation.
Swahili → Sukuma MT
Two open operating points on the same literary Swahili-Sukuma bitext (31,102 sentence pairs; document- group splits). Variants of small sequence-to-sequence models, not frontier LLMs, built for edge and remote devices. Scores are research-preview, not production translation. English is not a source language: pivot through Swahili first.
31,102
Train pairs
42.6
Quality chrF2
34.8
Lite chrF2
Checkpoints
Swahili → Sukuma MT (quality)
nileagi-suk-mt
Best held-out chrF2 on the literary bitext (chrF2 42.6, BLEU 20.0 on the document-group test set). One-way encoder-decoder; force start token suk_Latn with source swh_Latn. Default choice when quality matters and the device can hold a compact MT checkpoint.
View on Hugging FaceSwahili → Sukuma MT (lite)
nileagi-suk-mt-lite
Same table and recipe as quality, lighter footprint (chrF2 34.8, BLEU 12.7). Aimed at tighter edge and remote deployments where parameter count and memory dominate.
View on Hugging FaceCollection and org
The nileagi-suk collection groups Sukuma dataset and related small STT, TTS, and MT models. More NileAGI research models live on the organization page.
Hugging Face
Browse the Sukuma collection or the full NileAGI organization.
Related
- Blog: All Languages Matter — announcement, examples, and technical report download.
- Benchmarks — NILEAGI-SUB Swahili understanding evaluation.
- Inference (LM.C) — local models computing engine.