It may be desirable to have something compatible with the forward model. Currently there's an archive from here (ende.student.tiny.for.regression.tests) that is kept with separate specs from the usual pool (see https://github.com/browsermt/students/issues/37#issuecomment-842256130). Wouldn't mind having the same spec as the rest of the models here at the cost of discarding file based shortlists etc.
One kind of model required is a backward model (de -> en for existing en -> de) so an outbound translation example can be pointed to in code somewhere and runs on CI everytime (For https://github.com/browsermt/bergamot-translator/issues/78)
We have en->{et,es,cs} and {et,es,cs}->en. While I understand that generally we need to improve language support, you already have enough for testing purposes.
Need a few more distinct models to test applications enabled by multiple model capability (https://github.com/browsermt/bergamot-translator/issues/209, https://github.com/browsermt/bergamot-translator/pull/210).
It may be desirable to have something compatible with the forward model. Currently there's an archive from here (
ende.student.tiny.for.regression.tests
) that is kept with separate specs from the usual pool (see https://github.com/browsermt/students/issues/37#issuecomment-842256130). Wouldn't mind having the same spec as the rest of the models here at the cost of discarding file based shortlists etc.de -> en
for existingen -> de
) so an outbound translation example can be pointed to in code somewhere and runs on CI everytime (For https://github.com/browsermt/bergamot-translator/issues/78)xx->en
,en->yy
) if and when pivoting (https://github.com/browsermt/bergamot-translator/issues/212) comes into the picture.