Fix number of layers in Whisper export (#25375)
### Description
This PR fixes the number of hidden layers used during the export of
Whisper by always using the number of hidden layers in the decoder.
### Motivation and Context
Most of the Whisper models contain the same number of hidden layers in
the encoder and decoder. However, Whisper large v3 turbo contains 32
hidden layers in the encoder and only 4 hidden layers in the decoder.
This PR also fixes [this
issue](https://github.com/microsoft/onnxruntime-genai/issues/1611).
