Instructions to use onnx-community/whisper-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/whisper-base with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('automatic-speech-recognition', 'onnx-community/whisper-base');
Needs code
#3
by abdoeid - opened
Could you give the code used to export the vanilla whisper model into the onnx format? I know you used Optimum, but could you give more details about the q4 files to make it work on our fine-tuned version of Whisper?
Thank you very much, pointing to the commit saved us much time. Please add this to the Riddit post as it may add tangible value to the community.
abdoeid changed discussion status to closed