The main README is missing the "oved" option in OpenVino section

[pramodbiligiri]

I followed the instructions in the main README.md for OpenVino on Windows (https://github.com/ggerganov/whisper.cpp?tab=readme-ov-file#openvino-support), but my inference kept happening on the CPU. It worked after I added the "-oved GPU" option based on the description of the associated Pull Request: #1037 where it says:
"You can use -oved [DEVICE] argument to main to specify OpenVINO device to offload encoder inference to. For example:" (followed by an example).

Why is that last line left out of the main README? Is it a good idea to have it there as well?

[pramodbiligiri]

Also, the first line in the below logs when running OpenVino based inference says "No GPU found", whereas later it says using the GPU (see device = GPU in the last line below).

whisper_backend_init_gpu: no GPU found
whisper_init_state: kv self size  =    6.29 MB
whisper_init_state: kv cross size =   18.87 MB
whisper_init_state: kv pad  size  =    3.15 MB
whisper_init_state: compute buffer (conv)   =   16.26 MB
whisper_init_state: compute buffer (encode) =   85.86 MB
whisper_init_state: compute buffer (cross)  =    4.65 MB
whisper_init_state: compute buffer (decode) =   96.35 MB
whisper_ctx_init_openvino_encoder_with_state: loading OpenVINO model from 'models/ggml-base.en-encoder-openvino.xml'
whisper_ctx_init_openvino_encoder_with_state: first run on a device may take a while ...
whisper_openvino_init: path_model = models/ggml-base.en-encoder-openvino.xml, device = GPU, cache_dir = models/ggml-base.en-encoder-openvino-cache
whisper_ctx_init_openvino_encoder_with_state: OpenVINO model loaded

[foldl]

-oved is described here: https://github.com/ggerganov/whisper.cpp/blob/master/examples/cli/README.md

Still, it seems better to be included in the OpenVino section in the main README.