Igbo Speech Recognition

Igbo is the hardest of Orinode's six supported languages — 39.8% WER on Maraba v1 (May 2026). We're transparent about it: low-resource ASR for tonal languages with severe pre-training under-representation is genuinely difficult, and we publish the numbers rather than hide them.

Looking for the deployable product? This Igbo ASR model powers Maraba — an AI call agent that answers Igbo business calls, with ị/ụ/ọ sub-dot diacritics preserved and Igbo↔English code-switching handled per-token.

The Igbo language

Igbo is spoken by approximately 30 million people, primarily in southeastern Nigeria. Like Yorùbá, it is a tonal language — but Igbo has additional complexity:

Two-tone system with downstep — the same syllable can carry high, low, or downstepped-high tone, all phonemically distinct.
Vowel harmony — verbs alternate between two vowel sets based on a [±expanded pharynx] feature.
Severe pre-training scarcity — Whisper-large-v3 has no Igbo language token in its vocabulary. We repurposed the rarely-used Lingala (ln) slot and re-taught the model that signal == Igbo.
Diacritic-heavy orthography — Igbo's standard orthography uses sub-dot diacritics (ọ, ụ, ị) and tone marks; web text is often un-diacriticized, creating tokenizer mismatch.

Architecture notes

Igbo uses the same Speech-LLM stack as the other Maraba v1 languages — Whisper-large-v3 encoder + MLP adapter + Gemma-2-9b decoder + LoRA. The Igbo-specific engineering:

Token-slot remapping: Whisper's <|ln|> token is overloaded to mean Igbo. Inference must respect this mapping or the model emits Lingala-flavored output.
Dataset: Mozilla Common Voice 17 Igbo partition + Orinode-curated audio from Igbo radio archives and field recordings.
Tone-aware loss: standard cross-entropy with label smoothing 0.05.

Performance (May 2026)

Metric	Value	N
WER (normalized)	39.80%	200
WER (raw, case-sensitive)	45.11%	200

What we're doing about it

Igbo is the priority for Maraba v2 (target Q3–Q4 2026):

~100 hours of newly recorded studio Igbo audio across Onitsha, Enugu, and Owerri dialects.
Custom Igbo subword vocabulary (replacing the repurposed Lingala slot with a real Igbo token).
Tone-conditional acoustic modeling layer borrowed from recent African ASR research.
Target: under 25% WER on Igbo before Maraba v2 ship.

Get the model

Maraba v1 research weights including the Igbo configuration are on huggingface.co/Orinode. For pilot API access: [email protected].

For the deployable voice agent built on this model, see Maraba — Igbo AI at maraba.ai.