from the all hypothesis (lattice)
                using forward-filtering-and-backward-sampling algorithm.

            - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
              BPE-dropout.

    Examples:

    ```python
    >>> from transformers import MBart50Tokenizer

    >>> tokenizer = MBart50Tokenizer.from_pretrained("facebook/mbart-large-50", src_lang="en_XX", tgt_lang="ro_RO")
    >>> src_text = " UN Chief Says There Is No Military Solution in Syria"
    >>> tgt_text = "Şeful ONU declară că nu există o soluţie militară în Siria"
    >>> model_inputs = tokenizer(src_text, text_target=tgt_text, return_tensors="pt")
    >>> # model(**model_inputs) should work
    ```Z	input_idsZattention_maskÚ
prefix_tokensÚ
suffix_tokensNú