[Research] Speed up evaluation for XTREME-S #16785
Merged
Conversation
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
|
The documentation is not available anymore as the PR was closed or merged. |
anton-l
changed the title
|
@patrickvonplaten these are ready to merge now I think Also cc @sanchit-gandhi: the fixes should make your life much easier if you decide to do a run of multilingual translation :) |
patrickvonplaten
approved these changes
Apr 26, 2022
chamidullinr
pushed a commit
to chamidullinr/transformers
that referenced
this pull request
Apr 28, 2022
* Avoid repeated per-lang filtering * Language groups and logits preprocessing * Style
elusenji
pushed a commit
to elusenji/transformers
that referenced
this pull request
Jun 12, 2022
* Avoid repeated per-lang filtering * Language groups and logits preprocessing * Style
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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?
This adds a couple of improvements to the evaluation parts of the XTREME-S script:
preprocess_logits_for_metricsto transform the logits into pred_ids before concatenating them to avoid OOMs--language_groupparameter to train on the FLEURS dataset in batches of languages (west/eastern european languages, south asian languages etc.)Misc:
--ctc_zero_infinityto handle the noisy FLEURS transcriptions