ance, can be OOV for LM
            hotword_weight (`int`, *optional*):
                Weight factor for hotword importance Defaults to pyctcdecode's DEFAULT_HOTWORD_WEIGHT.
            alpha (`float`, *optional*):
                Weight for language model during shallow fusion
            beta (`float`, *optional*):
                Weight for length score adjustment of during scoring
            unk_score_offset (`float`, *optional*):
                Amount of log score offset for unknown tokens
            lm_score_boundary (`bool`, *optional*):
                Whether to have kenlm respect boundaries when scoring
            output_word_offsets (`bool`, *optional*, defaults to `False`):
                Whether or not to output word offsets. Word offsets can be used in combination with the sampling rate
                and model downsampling rate to compute the time-stamps of transcribed words.
            n_best (`int`, *optional*, defaults to `1`):
                Number of best hypotheses to return. If `n_best` is greater than 1, the returned `text` will be a list
                of lists of strings, `logit_score` will be a list of lists of floats, and `lm_score` will be a list of
                lists of floats, where the length of the outer list will correspond to the batch size and the length of
                the inner list will correspond to the number of returned hypotheses . The value should be >= 1.

                <Tip>

                Please take a look at the Example of [`~Wav2Vec2ProcessorWithLM.decode`] to better understand how to
                make use of `output_word_offsets`. [`~Wav2Vec2ProcessorWithLM.batch_decode`] works the same way with
                batched output.

                </Tip>

        Returns:
            [`~models.wav2vec2.Wav2Vec2DecoderWithLMOutput`].

        Example:
            See [Decoding multiple audios](#decoding-multiple-audios).
        r