training/flax/run_pseudo_labelling_pt.py [206:251]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        default="train+validation+test",
        metadata={
            "help": (
                "The name of the data set splits to use (via the datasets library)."
                " Defaults to 'train+validation+test'. Multiple splits can be passed by splitting a"
                " list through the '+' character, e.g. 'train+validation' will"
                " pseudo-label both the 'train' and 'validation' splits sequentially."
            )
        },
    )
    wandb_project: str = field(
        default="distil-whisper",
        metadata={"help": "The name of the wandb project."},
    )
    streaming: bool = field(
        default=False,
        metadata={"help": "Whether to use dataset's streaming mode to load and pre-process the data."},
    )
    max_samples_per_split: Optional[int] = field(
        default=None,
        metadata={"help": "For debugging purposes, truncate the number of examples per split to this value if set."},
    )
    return_timestamps: bool = field(
        default=False,
        metadata={
            "help": "Whether to return the timestamps with the text. This enables the `FlaxWhisperTimestampsLogitsProcessor`."
        },
    )
    language: str = field(
        default=None,
        metadata={
            "help": (
                "Language for multilingual distillation. This argument should be set for multilingual distillation "
                "only. For English speech recognition, it should be left as `None`."
            )
        },
    )
    task: str = field(
        default="transcribe",
        metadata={
            "help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."
            "This argument should be set for multilingual distillation only. For English speech recognition, it should be left as `None`."
        },
    )
    decode_token_ids: bool = field(
        default=True,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/run_pseudo_labelling.py [246:291]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        default="train+validation+test",
        metadata={
            "help": (
                "The name of the data set splits to use (via the datasets library)."
                " Defaults to 'train+validation+test'. Multiple splits can be passed by splitting a"
                " list through the '+' character, e.g. 'train+validation' will"
                " pseudo-label both the 'train' and 'validation' splits sequentially."
            )
        },
    )
    wandb_project: str = field(
        default="distil-whisper",
        metadata={"help": "The name of the wandb project."},
    )
    streaming: bool = field(
        default=False,
        metadata={"help": "Whether to use dataset's streaming mode to load and pre-process the data."},
    )
    max_samples_per_split: Optional[int] = field(
        default=None,
        metadata={"help": "For debugging purposes, truncate the number of examples per split to this value if set."},
    )
    return_timestamps: bool = field(
        default=False,
        metadata={
            "help": "Whether to return the timestamps with the text. This enables the `FlaxWhisperTimestampsLogitsProcessor`."
        },
    )
    language: str = field(
        default=None,
        metadata={
            "help": (
                "Language for multilingual distillation. This argument should be set for multilingual distillation "
                "only. For English speech recognition, it should be left as `None`."
            )
        },
    )
    task: str = field(
        default="transcribe",
        metadata={
            "help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."
            "This argument should be set for multilingual distillation only. For English speech recognition, it should be left as `None`."
        },
    )
    decode_token_ids: bool = field(
        default=True,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -