training/flax/run_distillation.py [267:340]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )
        },
    )
    max_duration_in_seconds: float = field(
        default=30.0,
        metadata={"help": ("Filter audio files that are longer than `max_duration_in_seconds` seconds")},
    )
    min_duration_in_seconds: float = field(
        default=0.0,
        metadata={"help": ("Filter audio files that are shorter than `min_duration_in_seconds` seconds")},
    )
    max_label_length: int = field(
        default=128,
        metadata={"help": "Truncate transcriptions that are longer `max_label_length` tokens."},
    )
    pad_target_to_multiple_of: Optional[int] = field(
        default=None,
        metadata={
            "help": (
                "If set will pad the target sequence to a multiple of the provided"
                " value. This is important to avoid triggering recompilations on TPU."
                " If unspecified, will default to padding the targets to max length."
            )
        },
    )
    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"
            )
        },
    )
    train_split_name: str = field(
        default="train",
        metadata={
            "help": ("The name of the training data set split to use (via the datasets library). Defaults to 'train'")
        },
    )
    eval_split_name: str = field(
        default="validation",
        metadata={
            "help": (
                "The name of the evaluation data set split to use (via the datasets"
                " library). Defaults to 'validation'"
            )
        },
    )
    wandb_project: str = field(
        default="distil-whisper",
        metadata={"help": "The name of the wandb project."},
    )
    wandb_name: str = field(
        default=None,
        metadata={"help": "The name of the wandb run."},
    )
    wandb_job_type: str = field(
        default="distil-whisper",
        metadata={"help": "The name of the wandb job type."},
    )
    wandb_dir: str = field(
        default=None,
        metadata={"help": "The absolute path to save the wandb logs."},
    )
    save_code_to_wandb: bool = field(
        default=False,
        metadata={
            "help": (
                "Whether to save main script to wandb. This is valuable for improving"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/flax/run_finetuning.py [198:271]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )
        },
    )
    max_duration_in_seconds: float = field(
        default=30.0,
        metadata={"help": ("Filter audio files that are longer than `max_duration_in_seconds` seconds")},
    )
    min_duration_in_seconds: float = field(
        default=0.0,
        metadata={"help": ("Filter audio files that are shorter than `min_duration_in_seconds` seconds")},
    )
    max_label_length: int = field(
        default=128,
        metadata={"help": "Truncate transcriptions that are longer `max_label_length` tokens."},
    )
    pad_target_to_multiple_of: Optional[int] = field(
        default=None,
        metadata={
            "help": (
                "If set will pad the target sequence to a multiple of the provided"
                " value. This is important to avoid triggering recompilations on TPU."
                " If unspecified, will default to padding the targets to max length."
            )
        },
    )
    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"
            )
        },
    )
    train_split_name: str = field(
        default="train",
        metadata={
            "help": ("The name of the training data set split to use (via the datasets library). Defaults to 'train'")
        },
    )
    eval_split_name: str = field(
        default="validation",
        metadata={
            "help": (
                "The name of the evaluation data set split to use (via the datasets"
                " library). Defaults to 'validation'"
            )
        },
    )
    wandb_project: str = field(
        default="distil-whisper",
        metadata={"help": "The name of the wandb project."},
    )
    wandb_name: str = field(
        default=None,
        metadata={"help": "The name of the wandb run."},
    )
    wandb_job_type: str = field(
        default="distil-whisper",
        metadata={"help": "The name of the wandb job type."},
    )
    wandb_dir: str = field(
        default=None,
        metadata={"help": "The absolute path to save the wandb logs."},
    )
    save_code_to_wandb: bool = field(
        default=False,
        metadata={
            "help": (
                "Whether to save main script to wandb. This is valuable for improving"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -