whisper : add OpenVINO support (#1037)

* openvino: use OpenVINO encoder inference

* openvino: add python script for OpenVINO model generation

* whisper: Fix 'unused' warnings when OpenVINO isn't enabled in build

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* whisper: Fix compilation error

* whisper: revert whisper_get_openvino_path_encoder & whisper_get_openvino_path_cache to non-const func signatures

* cmake: Add openvino-encoder as separate object target

* whisper : minor style fixes

* minor : indentation fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Ryan Metcalfe
2023-07-04 08:56:11 -04:00
committed by GitHub
parent 176d7e4e7b
commit 62b81276e0
8 changed files with 367 additions and 3 deletions

View File

@@ -110,6 +110,24 @@ extern "C" {
WHISPER_API struct whisper_state * whisper_init_state(struct whisper_context * ctx);
// 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 1 on success. If OpenVINO is not enabled in build, this
// simply returns 0.
WHISPER_API int whisper_ctx_init_openvino_encoder(
struct whisper_context * ctx,
const char * model_path,
const char * device,
const char * cache_dir);
// Frees all allocated memory
WHISPER_API void whisper_free (struct whisper_context * ctx);
WHISPER_API void whisper_free_state(struct whisper_state * state);