test: add non-zero CER/WER assertions for better metric coverage#16
Open
Julianblock wants to merge 1 commit into
Open
test: add non-zero CER/WER assertions for better metric coverage#16Julianblock wants to merge 1 commit into
Julianblock wants to merge 1 commit into
Conversation
The existing tests only exercise the zero-error (perfect prediction) branch of the CER torchmetric and the WER helper. Add: - test_cer_metric_nonzero: verifies the CER torchmetric returns 0.75 for a prediction of all-class-0 against a [0,1,2,3] reference (3/4 characters wrong), pinning normalisation and accumulation. - test_error_rates_nonzero: verifies compute_cer/compute_wer return correct positive values (all words wrong -> WER=1.0, half wrong -> WER=0.5, all chars wrong -> CER=1.0) and that the empty-reference guard still returns NaN.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The existing tests only exercise the zero-error (perfect prediction) branch of the CER torchmetric and the WER helper. Add:
test_cer_metric_nonzero: verifies the CER torchmetric returns 0.75 for a prediction of all-class-0 against a [0,1,2,3] reference (3/4 characters wrong), pinning normalisation and accumulation.
test_error_rates_nonzero: verifies compute_cer/compute_wer return correct positive values (all words wrong -> WER=1.0, half wrong -> WER=0.5, all chars wrong -> CER=1.0) and that the empty-reference guard still returns NaN.