Repository navigation
feat(se): add OpenBench speech enhancement metrics - #39
Conversation
|
Thanks for the implementation. After reviewing the route definitions, SE task pipeline, provider dispatch, documentation, local regression results, and the green Core workflow, I consider the overall direction and the added metrics acceptable. There is one concrete issue I would like you to address before merge: Required: incorrect metric metadata in multi-metric pipeline slotsFor example: build_pipeline_spec("se", metric="estoi,lsd")currently describes the slots as: The second slot should identify Optional robustness suggestionThe shared provider normalization layer could reject non-finite values ( The remaining reviewed items do not require changes for this PR: the default SE bundle is unchanged, the new routes are opt-in, the documentation and model/license limitations are described, and the current Core checks pass. After the slot metadata fix, please update the PR head and rerun Core; I will review the updated result before merge. |
Start Here
Read Contributing. If the category is unclear, use
Add Evaluation Capabilities.
Results:
10 passed545 passed, 67 skippedExact pipeline identity check:
The generated
report.jsonandpipeline_description.jsonpreserve the exactselected pipeline identity.
For heavyweight nodes, real A10 smoke tests were completed for DNSMOS, NISQA
DIM, SQUIM objective predictions, and LPS. Checkpoint-backed environment
assertions for unrelated existing nodes require their pre-existing model assets.
Safety
.venv, checkpoints, generated reports, local cache paths, or credentials committed