Welcome to the Beaker section.

This is the home for experiments we engage in at NNDI. Sometimes the techniques or technologies we present here may still be bleeding edge, in early/rapid-development or not yet production ready at the time of writing. The articles in this section are not meant to be tutorials and as such may assume some prior knowledge or context of whatever is being discussed. YMMV.
We hope the content in this section helps you learn a thing or two, as we share what we learn about different projects, tools and approaches.

Running Chichewa Speech to Text (STT) inference via ONNX

   |  4 minutes  |  848 words  |  NNDI

In this article, I will show how we converted Dunstan Matekenya’s Chichewa Whisper model to ONNX and running it within Python. Chichewa is one of the national languages of Malawi, fondly known as the warm heart of Africa. Our home. Chichewa is considered a low-resource language and there are not that many resources around transcription and audio based models for it. Fortunately, there is an ongoing effort to change this status quo, which we are eager to support by putting into practical implementation. [Read More]
onnx  python  ai  ml  whisper  openai  stt  transcription  chichewa  experiment  onnxruntime  dunstan matekenya