Yodi demoed across the international digital business fair, on every screen at the event.
A speech model behaves differently in a trade-show hall than on a test bench. That is exactly why it has to be taken there.
The UEMOA digital economy salon, in Lomé
SIPEN, the UEMOA international salon for digital economy professionals, moves capital each edition: Dakar in 2023, Abidjan in 2024, Lomé in 2025, Ouagadougou in 2026. The Togolese edition brought together digital players from the Union's eight member states.
Umbaji presented Yodi there, our speech AI model for West African languages. The demonstration ran on the salon's screens.
What a public demo teaches
Ambient noise, accents, overlapping voices, people speaking too close to or too far from the microphone: none of that shows up in a clean test set. It is nonetheless the real condition of use, and it is unforgiving.
- A model trained on quiet recordings stumbles in a room that is talking.
- A native speaker knows in a second whether the output is right — no metric is that fast.
- Whatever fails in public goes back into the corpus the next day.
It is also why we measure in public. Announcing that a model “supports” a language costs nothing; showing it to people who speak it is another exercise entirely. The Eyaa-Tom corpus and the Lom metric came out of that requirement.
A regional frame, not a national one
SIPEN gathers eight countries that share a currency, common regulatory frameworks and, to a large extent, cross-border languages. Ewe does not stop at the Ghanaian border; Mina and Bassar ignore administrative lines. A model useful in Togo is mechanically useful beyond it, which argues for building at that scale rather than one country at a time.
Running an event where Yodi would belong, or want to try it on your own use case? Request a demo.
