robust-speech-event/run_speech_recognition_ctc_bnb.py [208:260]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        metadata={
            "help": (
                "Filter audio files that are longer than `max_duration_in_seconds` seconds to"
                " 'max_duration_in_seconds`"
            )
        },
    )
    min_duration_in_seconds: float = field(
        default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
    )
    preprocessing_only: bool = field(
        default=False,
        metadata={
            "help": (
                "Whether to only do data preprocessing and skip training. This is especially useful when data"
                " preprocessing errors out in distributed training due to timeout. In this case, one should run the"
                " preprocessing in a non-distributed setup with `preprocessing_only=True` so that the cached datasets"
                " can consequently be loaded in distributed training"
            )
        },
    )
    use_auth_token: bool = field(
        default=False,
        metadata={
            "help": (
                "If :obj:`True`, will use the token generated when running"
                ":obj:`huggingface-cli login` as HTTP bearer authorization for remote files."
            )
        },
    )
    unk_token: str = field(
        default="[UNK]",
        metadata={"help": "The unk token for the tokenizer"},
    )
    pad_token: str = field(
        default="[PAD]",
        metadata={"help": "The padding token for the tokenizer"},
    )
    word_delimiter_token: str = field(
        default="|",
        metadata={"help": "The word delimiter token for the tokenizer"},
    )
    phoneme_language: Optional[str] = field(
        default=None,
        metadata={
            "help": (
                "The target language that should be used be"
                " passed to the tokenizer for tokenization. Note that"
                " this is only relevant if the model classifies the"
                " input audio to a sequence of phoneme sequences."
            )
        },
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



xtreme-s/run_xtreme_s.py [264:316]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        metadata={
            "help": (
                "Filter audio files that are longer than `max_duration_in_seconds` seconds to"
                " 'max_duration_in_seconds`"
            )
        },
    )
    min_duration_in_seconds: float = field(
        default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
    )
    preprocessing_only: bool = field(
        default=False,
        metadata={
            "help": (
                "Whether to only do data preprocessing and skip training. This is especially useful when data"
                " preprocessing errors out in distributed training due to timeout. In this case, one should run the"
                " preprocessing in a non-distributed setup with `preprocessing_only=True` so that the cached datasets"
                " can consequently be loaded in distributed training"
            )
        },
    )
    use_auth_token: bool = field(
        default=False,
        metadata={
            "help": (
                "If :obj:`True`, will use the token generated when running"
                ":obj:`huggingface-cli login` as HTTP bearer authorization for remote files."
            )
        },
    )
    unk_token: str = field(
        default="[UNK]",
        metadata={"help": "The unk token for the tokenizer"},
    )
    pad_token: str = field(
        default="[PAD]",
        metadata={"help": "The padding token for the tokenizer"},
    )
    word_delimiter_token: str = field(
        default="|",
        metadata={"help": "The word delimiter token for the tokenizer"},
    )
    phoneme_language: Optional[str] = field(
        default=None,
        metadata={
            "help": (
                "The target language that should be used be"
                " passed to the tokenizer for tokenization. Note that"
                " this is only relevant if the model classifies the"
                " input audio to a sequence of phoneme sequences."
            )
        },
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -