{{ message }}
Repository navigation
Conversation
* add an option while running eval to ignore the per record language in the manifest Signed-off-by: paarthneekhara <paarth.n@gmail.com> * ignore manifest language argument Signed-off-by: paarthneekhara <paarth.n@gmail.com> * restore context duration sampling during evaluation Use the configured duration range consistently instead of bypassing the minimum for test datasets. --------- Signed-off-by: paarthneekhara <paarth.n@gmail.com> (cherry picked from commit 3fd8beb) Signed-off-by: Jason <jasoli@nvidia.com>
* Add multilingual QA report support * Make context SSIM distribution optional * Check optional metric availability explicitly * Treat all-NaN optional metrics as unavailable (cherry picked from commit 81bedf3) Signed-off-by: Jason <jasoli@nvidia.com>
(cherry picked from commit 1ad45ed) Signed-off-by: Jason <jasoli@nvidia.com>
Signed-off-by: Jason <jasoli@nvidia.com>
1 of 17 tasks
This branch has not been deployed
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Evaluation manifests can contain language tags that differ from the corrected tags in the evalset configuration. Add an opt-in override to use the dataset or command-line language while preserving per-record manifest precedence by default.
Extend comparison reports to recognize multilingual QA datasets and handle unavailable optional similarity metrics and SFTP directory symlinks.
Collection: TTS
Changelog
--ignore_manifest_languagethrough inference dataset creation.Usage
Pass
--ignore_manifest_languagetoexamples/tts/magpietts_inference.pywhen the evalset or command-line language should take precedence. Omitting the flag retains the existing behavior for older models.Additional information
Brings #16238, #16242, and #16343 from the
2608_tts_trainingbranch to main. Formatting is folded into this bundle.