tokenizer_config.json

{
  "sp_model_kwargs": {
    "nbest_size": 6,
    "alpha": 0.1,
    "language": "en"
  },
  "src_lang": "en",
  "tgt_lang": "ff",
  "model_max_length": 512,
  "tokenizer_class": "MarianTokenizer",
  "unk_token": "<unk>",
  "bos_token": "<s>",
  "eos_token": "</s>",
  "pad_token": "<pad>",
  "mask_token": "<mask>",
  "additional_special_tokens": [
    "<pad>",
    "<unk>",
    "<s>",
    "</s>",
    "<mask>"
  ]
}