Conversion from Whisper to OpenVino failed

[ClaraSev1]

Hi there,

I have followed all instructions on the README document to use OpenVino. However, when I try to run python3 convert-whisper-to-openvino.py --model base.en, it gives me the following error:

/home/clara/whisper.cpp/models/openvino_conv_env/lib/python3.10/site-packages/whisper/model.py:166: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  assert x.shape[1:] == self.positional_embedding.shape, "incorrect audio shape"
Traceback (most recent call last):
  File "/home/clara/whisper.cpp/models/convert-whisper-to-openvino.py", line 55, in <module>
    convert_encoder(hparams, encoder, args.model)
  File "/home/clara/whisper.cpp/models/convert-whisper-to-openvino.py", line 32, in convert_encoder
    encoder_model = mo.convert_model(onnx_path, compress_to_fp16=True)
  File "/home/clara/whisper.cpp/models/openvino_conv_env/lib/python3.10/site-packages/openvino/tools/mo/convert.py", line 364, in convert_model
    ov_model, _ = _convert(cli_parser, framework, params, True)
  File "/home/clara/whisper.cpp/models/openvino_conv_env/lib/python3.10/site-packages/openvino/tools/mo/convert_impl.py", line 957, in _convert
    raise e.with_traceback(None)
TypeError: load(): incompatible function arguments. The following argument types are supported:
    1. (self: openvino._pyopenvino.FrontEnd, path: object) -> ov::frontend::InputModel

Invoked with: <FrontEnd 'onnx'>, '/home/clara/whisper.cpp/models/onnx_encoder/whisper_encoder.onnx', False

Does anyone have any experience with this type of error? I don't know how to proceed. Any help will be appreciated.
Thank you.