Open models
Research-preview weights on Hugging Face. Small models for African languages and edge settings: Sukuma speech recognition, text-to-speech, and Swahili→Sukuma machine translation.
Sukuma Speech → Text
Two Whisper-based operating points for literary Sukuma speech recognition (document-group splits). Research preview scores on read-aloud single-speaker audio, not conversational or multi-speaker ASR.
16,792
Train windows
21.3%
Quality WER
26.1%
Lite WER
Sukuma Text → Speech
Two operating points for literary Sukuma text-to-speech in macron orthography. Research preview: input must be Sukuma text; for Swahili → speech, translate with MT first.
Swahili → Sukuma Machine Translation
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.
31,102
Train pairs
42.6
Quality chrF2
34.8
Lite chrF2
Checkpoints
Sukuma Text → Speech (quality)
nileagi-suk-tts
Sukuma TTS for literary macron orthography (ā ē ī ō ū). Research preview; prefer Sukuma text, not English or raw Swahili. For Swahili → speech, translate with MT first.
View on Hugging FaceSukuma Text → Speech (lite)
nileagi-suk-tts-lite
Same Sukuma TTS recipe as quality, lighter footprint for tighter edge and remote deployments.
View on Hugging FaceSukuma Speech → Text (quality)
nileagi-suk-stt
Whisper-based Sukuma ASR for literary read-aloud speech (WER 21.3%, CER 4.9% on the document-group test). Prefer 16 kHz mono; not English or Swahili ASR.
View on Hugging FaceSukuma Speech → Text (lite)
nileagi-suk-stt-lite
Same Sukuma ASR recipe as quality, lighter footprint (WER 26.1%, CER 6.4%). Aimed at tighter edge and remote deployments.
View on Hugging FaceSwahili → Sukuma Machine Translation (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 Machine Translation (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: Giving Sukuma a Voice · TTS announcement, try box, and technical report.
- Blog: Listening for Sukuma · STT announcement, try box, and technical report.
- Blog: All Languages Matter · MT announcement, examples, and technical report.
- TTS technical report (PDF) · training, evaluation, and limits for Sukuma text-to-speech.
- STT technical report (PDF) · training, evaluation, and limits for Sukuma speech recognition.
- MT technical report (PDF) · training, evaluation, and limits for Swahili-to-Sukuma translation.
- Preview: Sukuma STT · record, upload, samples, settings, and code.
- Preview: Sukuma TTS · speak Sukuma text, settings, and Transformers script.
- Preview: Sukuma MT · translate, settings, and Transformers script.
- Benchmarks · NILEAGI-SUB Swahili understanding evaluation.
- Inference (LM.C) · local models computing engine.