Resume translation and max generation logic#36
Merged
Conversation
Removing the option restraining output length appears to fix translation errors where the model did not appear to complete its generation but instead repeatedly output the same ending phrase.
This reverts commit 022d12b.
tanhaow
approved these changes
Feb 24, 2026
tanhaow
left a comment
tanhaow
left a comment
There was a problem hiding this comment.
Thank you for adding the new feature 🚀
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Associated Issue(s): N/A
Changes in this PR
translate.pyso that HuggingFace translate functions all set themax_new_tokensfield for generation to double the input length.translate_corpus.pyso that translation can be continued if the script is disrupted (e.g., fail to connect to the Google Cloud server)Reviewer Checklist
translate_corpus.pyruns successfully without resumingtranslate_corpus.pywith resume runs successfully. Confirm that existing translations are skipped and the rest are translated