Why I Started Sauti Labs

Описание и применение

Автор создал Sauti Labs, чтобы преодолеть пробелы в доступных и коммерчески пригодных системах распознавания речи для африканских языков, используя существующие исследовательские ресурсы и разрабатывая собственные решения.

Задача

Speech recognition models like OpenAI’s Whisper perform poorly on African languages and accents, limiting the ability to build reliable voice services for African communities.

Результат

The author founded Sauti Labs to develop production‑ready speech and language AI for African languages, addressing gaps in accuracy, licensing, and deployment that existing research resources do not fully cover.

Рабочий процесс

• 1. Build Scribe AI using Whisper for ASR.
• 2. Evaluate Whisper’s performance on African languages.
• 3. Search for alternative models and datasets.
• 4. Discover community resources (Masakhane, Maseno, Lelapa AI).
• 5. Identify limitations: lack of models for specific use cases, high error rates, restrictive licenses, hardware constraints.
• 6. Decide to create Sauti Labs to bridge research and product gaps for African languages.

Доказательства

In July 2026, I was building Scribe AI, an offline system that listens to a church service and puts the scripture being referenced on screen. Everything in it depends on speech recognition, and for that I used OpenAI’s Whisper.

Источник

Whisper’s training data is heavily concentrated in English. Swahili appears with roughly five hours of transcribed speech, while Dholuo—the language that first drew me into this work—is absent from its supported-language list.

Источник

Masakhane, a grassroots community focused on strengthening natural language processing research in African languages, has spent years building open datasets, models, and benchmarks.

Источник

The products that did exist had been built, sensibly, around particular languages and markets. That is how products should start, but it still left the speech I needed uncovered.

Источник