Ẹtí: An Open-Source Yoruba Speech Recognition Model

Yoruba is spoken by roughly 50 million people across West Africa and the diaspora — and yet it has almost no commercial speech recognition coverage. Mainstream ASR models still struggle with it, and openly licensed Yoruba models are rare. That gap is exactly what we set out to fill.

Today we're releasing Ẹtí — our open-source Yoruba automatic speech recognition model — under the MIT license. It's a Whisper-small model fine-tuned for Yoruba, published in both Transformers and CTranslate2 formats so it runs on a laptop CPU as easily as on a GPU server.

"Ẹtí means 'ear' in Yoruba. It's our small step toward giving one of Africa's most spoken languages a real, open ASR baseline."

Why Yoruba ASR

Speech recognition is the front door to a whole category of products — voice assistants, call-centre automation, transcription, accessibility tools. When a language has no usable ASR, its speakers are locked out of those products. Yoruba, with tens of millions of speakers, deserves better than a shrug.

This is also a core part of what we're building at DevBlock: African-language voice agents. An agent can't listen if there's no ear. Ẹtí is that ear — the first openly licensed piece of the stack.

The Model

Ẹtí starts from OpenAI's Whisper-small (MIT) and adapts it with LoRA on the q_proj and v_proj projection layers (rank 16, alpha 32), which we then merge back into the base. The result keeps Whisper's ~244M parameters but is tuned to understand Yoruba the way speakers actually talk.

We ship two formats in one repository: the standard Transformers model, and a CTranslate2 int8 build (248MB) for faster-whisper — so you can run it on a commodity CPU with no GPU at all.

Training Data

The model was trained on a mix of read speech, news audio (IroyinSpeech, CC-BY 4.0 — attribution to its contributors), and a capped sample of WAXAL. The model card documents every source and license, with a clear note to verify terms before commercial use.

Honest Numbers

We published held-out WER results rather than cherry-picked ones. On read speech, Ẹtí scores 0.47 WER (no-diacritics); on conversational Yoruba — far harder — it scores 0.82. That's a clear, honest picture: a strong open baseline that still has a long way to go on spontaneous speech.

That gap is the most valuable insight in the model card: conversational data is where the community's contributions will matter most.

What's Next

This is v0.1 of a longer roadmap. Next up: more conversational training data, a larger base model, and then the rest of the voice-agent stack — and eventually the same treatment for other African languages.

Ẹtí is MIT-licensed and free to use. Contributions, feedback, and datasets welcome.

Model: huggingface.co/devblockHQ/eti-yoruba-asr

Code: github.com/DEVBLOCK-TECHNOLOGIES-LIMITED/eti-yoruba-asr