ONNX implementation

#17
by kirankumaram - opened

Can anyone suggest how to use the exported whisper-large model in ONXX version for transcription or translation?

You can use it with ORT pipeline: https://github.com/huggingface/optimum/pull/420#issue-1406136285

Or ONNX runtime: https://huggingface.co/docs/transformers/serialization#exporting-a-model-to-onnx (here you'll need to modify the template code snippet to pass the appropriate inputs to the ONNX model)

Sign up or log in to comment