Skip to content

NPU Whisper switch to use stateful pipeline by default #3085

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
eshiryae wants to merge 4 commits into
base: master
Choose a base branch
from
Open

NPU Whisper switch to use stateful pipeline by default #3085

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1828f2c
NPU Whisper switch to use stateful pipeline by default
eshiryae Nov 28, 2025
efcc298
Fix config for static tests
eshiryae Nov 28, 2025
3966808
Merge branch 'master' into npu_whisper_to_stateful
eshiryae Nov 28, 2025
dceabed
Address comments
eshiryae Dec 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/cpp/src/whisper/pipeline.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,7 @@ ov::genai::WhisperPipeline::WhisperPipeline(const std::filesystem::path& models_
auto start_time = std::chrono::steady_clock::now();
if (device == "NPU") {
auto properties_copy = properties;
const bool use_static_pipeline = utils::pop_or_default(properties_copy, "STATIC_PIPELINE", true);
const bool use_static_pipeline = utils::pop_or_default(properties_copy, "STATIC_PIPELINE", false);
if (!use_static_pipeline) {
m_impl = std::make_unique<WhisperPipelineStatefulImpl>(models_path, device, properties_copy);
} else {
Expand Down
3 changes: 2 additions & 1 deletion tests/python_tests/test_whisper_pipeline_static.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,8 @@
# and robustness of the WhisperStaticPipeline on NPUW:CPU.
config = {"NPU_USE_NPUW" : "YES",
"NPUW_DEVICES" : "CPU",
"NPUW_ONLINE_PIPELINE" : "NONE"}
"NPUW_ONLINE_PIPELINE" : "NONE",
"STATIC_PIPELINE": True}

def load_and_save_whisper_model(params, stateful=False, **tokenizer_kwargs):
model_id, path = params
Expand Down
Loading