ONNX Model Zoo

kostasang/whisper-large-v3-turbo-onnx-base

By kostasang · ↓ 0 · ♥ 0 · Updated 2026-02-05

What's in this repo

This page lists the files in kostasang/whisper-large-v3-turbo-onnx-base, including decoder_model.onnx, decoder_with_past_model.onnx, encoder_model.onnx.

  • 3 ONNX models (.onnx files)
  • 16 files, including 9 .json, 3 .onnx, 1 .md, 1 .onnx_data, 1 .txt
  • Last updated 2026-02-05

ONNX files

File Size Download
decoder_model.onnx — Download
decoder_with_past_model.onnx — Download
encoder_model.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

whisper-large-v3-turbo-onnx-base

This is a Base ONNX (FP32) version of openai/whisper-large-v3-turbo.

Model Details

Size Comparison

Version Size
Base ONNX (FP32) 4198.51 MB ←
FP16 ONNX 2099.54 MB
INT8 Quantized ONNX 1459.58 MB
Compression 1.00x

Usage

from optimum.onnxruntime import ORTModelForSpeechSeq2Seq
from transformers import AutoProcessor

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

Model info

optimum
optimum onnx whisper speech-recognition fp32 base_model:openai/whisper-large-v3-turbo base_model:quantized:openai/whisper-large-v3-turbo region:us
↓ 0 ♥ 0

Created: 2026-02-05

Updated: 2026-02-05

View on Hugging Face

Files (16)

.gitattributes
README.md
added_tokens.json
config.json
decoder_model.onnx ONNX
decoder_with_past_model.onnx ONNX
encoder_model.onnx ONNX
encoder_model.onnx_data
generation_config.json
merges.txt
normalizer.json
preprocessor_config.json
special_tokens_map.json
tokenizer.json
tokenizer_config.json
vocab.json

Related models

More from kostasang

More models

No task type declared.

Popular models