whisper_ctx_init_openvino_encoder_with_state method

int whisper_ctx_init_openvino_encoder_with_state(
  1. Pointer<whisper_context> ctx,
  2. Pointer<whisper_state> state,
  3. Pointer<Char> model_path,
  4. Pointer<Char> device,
  5. Pointer<Char> cache_dir,
)

Given a context, enable use of OpenVINO for encode inference. model_path: Optional path to OpenVINO encoder IR model. If set to nullptr, the path will be generated from the ggml model path that was passed in to whisper_init_from_file. For example, if 'path_model' was "/path/to/ggml-base.en.bin", then OpenVINO IR model path will be assumed to be "/path/to/ggml-base.en-encoder-openvino.xml". device: OpenVINO device to run inference on ("CPU", "GPU", etc.) cache_dir: Optional cache directory that can speed up init time, especially for GPU, by caching compiled 'blobs' there. Set to nullptr if not used. Returns 0 on success. If OpenVINO is not enabled in build, this simply returns 1.

Implementation

int whisper_ctx_init_openvino_encoder_with_state(
  ffi.Pointer<whisper_context> ctx,
  ffi.Pointer<whisper_state> state,
  ffi.Pointer<ffi.Char> model_path,
  ffi.Pointer<ffi.Char> device,
  ffi.Pointer<ffi.Char> cache_dir,
) {
  return _whisper_ctx_init_openvino_encoder_with_state(
    ctx,
    state,
    model_path,
    device,
    cache_dir,
  );
}