Microsoft.ML.OnnxRuntime.OnnxRuntimeException: "[ErrorCode:InvalidGraph] Load model Error Node (BeamSearch_node) has input size 12 not in range [min=5, max=10]

[DimQ1]

Describe the issue

What happened?
I try to run example https://github.com/onnxruntime/Whisper-HybridLoop-Onnx-Demo

I followed the instructions and converted the Whisper model.

Run example and get the following error:

Microsoft.ML.OnnxRuntime.OnnxRuntimeException: "[ErrorCode:InvalidGraph] Load model from E:\Work\Dimq1\source\OpenAI\Whisper-HybridLoop-Onnx-Demo\AudioNoteTranscription\bin\Debug\net8.0-windows7.0\Onnx\model.onnx failed:This is an invalid model. In Node, ("BeamSearch_node", BeamSearch, "com.microsoft", -1) : ("log_mel": tensor(float),"max_length": tensor(int32),"min_length": tensor(int32),"num_beams": tensor(int32),"num_return_sequences": tensor(int32),"length_penalty": tensor(float),"repetition_penalty": tensor(float),"","","","","",) -> ("sequences",) , Error Node (BeamSearch_node) has input size 12 not in range [min=5, max=10]."

At the same time onnx model which I get as a resul work fine with python.

To reproduce

Follow instractions from source
https://github.com/DimQ1/Whisper-HybridLoop-Onnx-Demo/tree/shdmitry/test-onnx-whisper-tiny

model.zip.001.zip
model.zip.002.zip

Urgency

No response

Platform

Windows

OS Version

11

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

1.16.2

ONNX Runtime API

C#

Architecture

X64

Execution Provider

Default CPU

Execution Provider Library Version

No response

[DimQ1]

I resolve the issue using correct nugets