Open research for Somali AI
How we do Somali NLP research — open methodology, reproducible results, peer-ready papers, and the SomBench evaluation suite.
Every language deserves AI infrastructure. We build it for Somali first — openly, and to a standard the field can trust.
Open by default
Datasets, model weights, and evaluation code are released openly so anyone can build, verify, and improve them.
Community-owned
The people who speak the language help build the technology — and own its direction.
Rigorous & reproducible
Clear benchmarks, documented methods, and results others can reproduce and extend.
Four layers of the Somali AI stack
From raw data to deployable models and the research that holds it all to a standard.
Datasets
Open, permissively licensed Somali text, speech, and document corpora built for training and evaluation.
Speech Technology
ASR and TTS for Somali — turning radio, calls, and conversation into usable text, and text back into natural voice.
Foundation Models
Tokenizers and language models adapted to Somali morphology, dialects, and scripts — efficient and open.
Research
Benchmarks, evaluation suites, and reproducible studies advancing low-resource NLP for African languages.
Research papers
SomBench: A Benchmark for Somali Natural Language Processing
Yusuf S., Tood O. · In preparation · 2026
Abstract
We present SomBench, the first comprehensive evaluation benchmark for Somali NLP, covering classification, NER, translation, summarisation, and ASR. We evaluate six models and establish baselines for future work.
Low-resource ASR for Somali: Corpus Design and Whisper Fine-tuning
Tood O., Yusuf S. · In preparation · 2026
Abstract
We describe the construction of a 320-hour Somali speech corpus and show that fine-tuning Whisper on this data reduces WER by 41% over the zero-shot baseline, establishing a new state of the art on Somali ASR.
Subword Tokenisation for Agglutinative Somali
Yusuf S., Tood O. · In preparation · 2025
Abstract
We study the impact of BPE, Unigram, and morphology-aware tokenization on downstream Somali NLP tasks and show that morphology-informed models reduce out-of-vocabulary rates by 33% and improve classification F1 by up to 6 points.
New from the lab
Jul 2026
Soplang v2.0.0
A compiler for the first Somali programming language — native Somali keywords, a Cranelift JIT, and ahead-of-time native builds.
Jun 2026
SomNLP-Corpus v2
Expanded to 887M+ tokens with a six-source cleaning pipeline and LID verification.
May 2026
whisper-som-small (ASR)
A Somali speech-to-text checkpoint reaching 11.4% WER on held-out radio audio.
Nov 2025
Tokenization for Somali morphology
A study of subword strategies for an agglutinative, low-resource language.
Mar 2026
SomBench v0.1 evaluation suite
A first public benchmark for Somali NLP across six core tasks.
Q3 2026
Somali TTS voice (preview)
Natural Somali speech synthesis, opening for early research access.
Benchmark results
Internal preview benchmarks on held-out data. Model weights and eval scripts releasing publicly soon.
| Task | Type | Metric | Score | Model | Status |
|---|---|---|---|---|---|
| ASR (clean) | Speech | WER ↓ | 11.4 | whisper-som-small | preview |
| ASR (noisy) | Speech | WER ↓ | 18.7 | whisper-som-small | preview |
| NER | NLP | F1 | 78.4 | goobo-base | preview |
| POS Tagging | NLP | Accuracy | 86.2 | goobo-base | preview |
| Sentiment | NLP | F1 | 82.1 | goobo-base | preview |
| Summarization | NLP | ROUGE-L | — | som-sum | upcoming |
| Translation (som→en) | NLP | BLEU | 24.3 | som-en-mt | preview |
The domains we work across
A full-stack research practice spanning language, speech, and retrieval — built for low-resource settings.
NLP
Tagging, parsing, NER
ASR
Speech to text
TTS
Text to speech
LLMs
Language models
Tokenizers
Subword for Somali
Benchmarks
Task suites
Evaluation
Rigorous metrics
RAG
Grounded retrieval
Speech Processing
Alignment & diarization
Build Somali AI in the open
Use our datasets and models, contribute to the research, or partner with the lab. Everything we can open, we do.