[codex] Add score config validation#9
Closed
ftshijt wants to merge 154 commits into
Closed
Conversation
…able-scoring Document resumable scoring
…d-scoring Add metric-oriented scoring mode
Fix speaker metric import side effects
…ckaging-ci Refine packaging CI and metric summaries
…o-audio-extra [codex] Move fastdtw to audio extra
…o-audio-extra Make real metric caches explicit
…-real-fadtk-tests Add registry-backed distributional metrics tests
# Conflicts: # docs/supported_metrics.md # versa/__init__.py # versa/metrics.py # versa/scorer_shared.py
…/songeval Add songeval
Add MultiGauss
…etric-migration Settle metric OO migration cleanup
…ic-discovery-cli Add metric discovery CLI
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
9 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closed in favor of the upstream-targeted PR for this change.
Original body:
Summary
Adds a preflight validator for YAML score configs so users get clear, actionable errors before audio loading, metric setup, or scoring begins.
The validator now catches:
--gt--text--use_gpuThe CLI scorer and chunked scorer both run validation immediately after YAML parsing. The dependency handling also falls back to metadata discovery for metrics whose optional backend cannot be imported, so those cases report as missing dependencies instead of misleading unknown metrics.
Validation
.codex-test-venv/bin/python -m pytest test/test_metrics/test_definition.py -q.codex-test-venv/bin/python -m py_compile versa/config_validation.py versa/bin/scorer.py versa/bin/scorer_chunk.py