Helsinki-NLP/Tatoeba-Challenge

Issues

• Korean support for mul-en model

  #38 opened 2 months ago by vonjackustc
  0

• Bopo script detection

  #37 opened 6 months ago by shaoxiongji
  0

• En-to-es model doesn't work

  #32 opened 7 months ago by ng1402
  1

• nobody trained the model for eng-san (sanskrit)?

  #36 opened 8 months ago by rcappuccio
  1

• Tatoeba models outputting nonsense

  #35 opened 10 months ago by Latrolage
  6

• How to convert models with two vocab files to PyTorch?

  #22 opened 3 years ago by phiradet
  6

• How am I supposed to run the models?

  #34 opened a year ago by Latrolage
  1

• dataset of Helsinki-NLP/opus-mt-en-zh

  #20 opened a year ago by QzzIsCoding
  1

• encdoing issue

  #31 opened a year ago by 106AbdulBasit
  2

• NOR-to-ENG model does not exist on Huggingface

  #33 opened a year ago by HarinderIndicate
  0

• there are error when i load the tokenizer : tokenizer = MarianTokenizer.from_pretrained(model_name)

  #30 opened a year ago by ccw7463
  0

• convert_marian_tatoeba_to_pytorch FileNotFoundError

  #28 opened 2 years ago by Lyaaaaaaaaaaaaaaa
  5

• Special characters are not allowed when converting the last fin-eng model to pytorch

  #16 opened 2 years ago by avostryakov
  7

• Batch-mode prediction

  #8 opened 2 years ago by antoine-isnardy-danone
  2

• Abk-Eng

  #9 opened 2 years ago by QazQazaq
  3

• Finetune huggingface models example

  #18 opened 2 years ago by omrishsu
  1

• Bigger models

  #15 opened 2 years ago by avostryakov
  6

• Caucasian Languages Corpus

  #10 opened 2 years ago by Plkmoi
  1

• How do i use these models?

  #24 opened 2 years ago by Hammyhamm89
  11

• uzb-eng - Invalid download link

  #27 opened 2 years ago by ples
  3

• License clarification

  #29 opened 2 years ago by Godnoken
  2

• Where is the testset data?

  #26 opened 2 years ago by David-hg
  4

• Issue with the download of the latest French-English (Fr-En) model

  #25 opened 3 years ago by maxiek0071
  3

• question on reproduce model

  #23 opened 3 years ago by jackie930
  2

• Prediction errors using pre-trained eng-kor model

  #21 opened 3 years ago by amesval
  1

• Results is always in English

  #19 opened 3 years ago by omrishsu
  1

• About MarianTokenizer

  #17 opened 3 years ago by hieutt99
  0

• Eng to Chinese translation weird behaviour when translating single word

  #13 opened 3 years ago by LeeDustin
  6

• Use tensorflow 2.x can not load the offline model

  #14 opened 3 years ago by iDustPan
  2

• How to load and use the model?

  #2 opened 4 years ago by jingmouren
  5

• Missing particular language pair: eng-deu

  #7 opened 4 years ago by bricksdont
  2

• Dataset server down?

  #6 opened 4 years ago by dannigt
  2

• Indonesian missing?

  #5 opened 4 years ago by jvamvas
  2

• some module have missed

  #4 opened 4 years ago by zhhao1
  3

• Download data for specific language pair

  #3 opened 4 years ago by bricksdont
  1

• Question about the training data

  #1 opened 4 years ago by luofuli
  2