# Introduction

This folder contains code showing how to convert [Whisper][whisper] to onnx
and use onnxruntime to replace PyTorch for speech recognition.

You can use [sherpa-onnx][sherpa-onnx] to run the converted model.

Please see
https://k2-fsa.github.io/sherpa/onnx/pretrained_models/whisper/export-onnx.html
for details.

[whisper]: https://github.com/openai/whisper
[sherpa-onnx]: https://github.com/k2-fsa/sherpa-onnx