tokenizer_config.json

{
  "clean_up_tokenization_spaces":true,
  "eos_token":"</s>",
  "model_max_length":512,
  "pad_token":"<pad>",
  "separate_vocabs":false,
  "source_lang":"cy",
  "target_lang":"en",
  "tokenizer_class":"MarianTokenizer",
  "unk_token":"<unk>"
}