training/flax/run_eval.py [161:201]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )
    dataset_config_name: Optional[str] = field(
        default=None,
        metadata={"help": "The configuration name of the dataset to use (via the datasets library)."},
    )
    dataset_split_name: Optional[str] = field(
        default=None,
        metadata={"help": "The split name of the dataset to use (via the datasets library)."},
    )
    dataset_cache_dir: Optional[str] = field(
        default=None,
        metadata={"help": "Path to cache directory for saving and loading datasets"},
    )
    overwrite_cache: bool = field(
        default=False,
        metadata={"help": "Overwrite the cached training and evaluation sets"},
    )
    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={"help": "The number of processes to use for the preprocessing."},
    )
    audio_column_name: str = field(
        default="audio",
        metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
    )
    text_column_name: str = field(
        default=None,
        metadata={"help": "The name of the dataset column containing the text data. Defaults to `text`."},
    )
    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."},
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/flax/run_speed_pt.py [133:173]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )
    dataset_config_name: Optional[str] = field(
        default=None,
        metadata={"help": "The configuration name of the dataset to use (via the datasets library)."},
    )
    dataset_split_name: Optional[str] = field(
        default=None,
        metadata={"help": "The split name of the dataset to use (via the datasets library)."},
    )
    dataset_cache_dir: Optional[str] = field(
        default=None,
        metadata={"help": "Path to cache directory for saving and loading datasets"},
    )
    overwrite_cache: bool = field(
        default=False,
        metadata={"help": "Overwrite the cached training and evaluation sets"},
    )
    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={"help": "The number of processes to use for the preprocessing."},
    )
    audio_column_name: str = field(
        default="audio",
        metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
    )
    text_column_name: str = field(
        default=None,
        metadata={"help": "The name of the dataset column containing the text data. Defaults to `text`."},
    )
    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."},
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -