ONNX version of whisper-large-v3-onnx-fp16

This repository contains the ONNX version of the openai/whisper-large-v3 model.

Model Details

The original model can be found here: openai/whisper-large-v3

This is the unquantized FP16 version of the model, offering the highest precision.

Usage

The model can be used with optimum.onnxruntime.ORTModelForSpeechSeq2Seq.

from optimum.onnxruntime import ORTModelForSpeechSeq2Seq
from transformers import WhisperProcessor

model_name = "mirekphd/whisper-large-v3-onnx-fp16"
processor = WhisperProcessor.from_pretrained(model_name)
model = ORTModelForSpeechSeq2Seq.from_pretrained(model_name)

# ... add your inference code here ...