metadata

tags:
  - translation
inference:
  parameters:
    src_lang: en_XX
    tgt_lang: is_IS
    decoder_start_token_id: 250012
    max_length: 512
widget:
  - text: I once owned a horse. It was black and white.
language:
  - en
  - is
datasets:
  - >-
    train.fornsogur,train.greynir_articles,train.greynir_articles_2021,train.hirslan,train.ic3_filtered,train.rafbokavefurinn,train.rmh_filtered,train.wikipedia,train.abstracts,train.studentabladid,train.jw300,train.rannsoknarskyrsla_althingis,train.eea,train.fornsogur,train.greynir_articles,train.greynir_articles_2021,train.hirslan,train.ic3_filtered,train.rafbokavefurinn,train.rmh_filtered,train.wikipedia,train.bible

mBART based translation model

This is the same model as are provided on CLARIN: https://repository.clarin.is/repository/xmlui/handle/20.500.12537/278

model_path: /data/scratch/haukur/document_translation/checkpoints/v2.all.wordnoise0.06.fragmentnoise0.06.lr8e-06.dropout0.1.spmalpha0.7.seed228/checkpoint_best.pt
num_updates: 14500
Source language: en_XX
Target language: is_IS