✳PROJECT / SPEECH RECOGNITION03 / ZAZO AI
Where research meets use.
Read the scope, status, current outputs and attribution notes for this project.
RESEARCH-LED · APPLICATION-FOCUSEDHAVE A PROJECT IN MIND? ↗
Chichewa speech-to-text research
Adapting speech recognition models for local language data.
Project overview
Work dating from 2022 combines speech dataset preparation, transcript normalization, model adaptation, training and evaluation, including fine-tuning Whisper large-v3. Earlier public models and code are credited to Dunstan Matekenya.
Status, limitations and credit
The public releases are research resources, not claims of production readiness or verified accuracy for every use case.
← Back to all projectsTHE NEXT CONVERSATION
Discuss your project A similar challenge in your organization?
We can discuss research collaboration, data collection, language technology and specific deployment needs.