Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Replace the default model for BackTranslationAugmenter #10

Open
chck opened this issue Oct 4, 2021 · 2 comments
Open

Replace the default model for BackTranslationAugmenter #10

chck opened this issue Oct 4, 2021 · 2 comments

Comments

@chck
Copy link
Owner

chck commented Oct 4, 2021

Because Helsinki-NLP supports the only bible texts, not the regular ones.
https://github.com/chck/AugLy-jp/blob/main/augly_jp/text/augmenters/sentence.py#L33-L37
@chck chck changed the title Fix the default model for BackTranslationAugmenter Replace the default model for BackTranslationAugmenter Oct 4, 2021
@chck
Copy link
Owner Author

chck commented Oct 4, 2021 •
edited
Loading

Candidates:
https://github.com/MorinoseiMorizo/jparacrawl-finetune

It is necessary to make sure the way to generate via the model.
Because this repo refers to the old fairseq/generate.py which is not in current fairseq.

@chck
Copy link
Owner Author

chck commented Jan 27, 2022

Ref. http://phontron.com/japanese-translation-data.php

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@chck