whisper-large-v3-turbo-onnx-fp16

This is a FP16 ONNX version of openai/whisper-large-v3-turbo.

Model Details

• Base Model: openai/whisper-large-v3-turbo
• Format: ONNX (FP16)
• Architecture: arm64

Size Comparison

Version	Size
Base ONNX (FP32)	4198.51 MB
FP16 ONNX	2099.54 MB ←
INT8 Quantized ONNX	1459.58 MB
Compression	2.00x

Usage

from optimum.onnxruntime import ORTModelForSpeechSeq2Seq
from transformers import AutoProcessor

model = ORTModelForSpeechSeq2Seq.from_pretrained("kostasang/whisper-large-v3-turbo-onnx-fp16")
processor = AutoProcessor.from_pretrained("kostasang/whisper-large-v3-turbo-onnx-fp16")