training/flax/run_long_form_transcription.py [164:252]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class DataTrainingArguments:
    """
    Arguments pertaining to what data we are going to input our model for training and eval.
    """

    dataset_name: str = field(
        default=None,
        metadata={
            "help": "The name of the dataset to use (via the datasets library). Load and combine "
            "multiple datasets by separating dataset hours by a '+' symbol."
        },
    )
    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"},
    )
    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_label_length: int = field(
        default=256,
        metadata={"help": "Truncate transcriptions that are longer `max_label_length` tokens."},
    )
    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"
                " experiment reproducibility and to diff code across experiments in"
                " the UI."
            )
        },
    )
    streaming: bool = field(
        default=True,
        metadata={"help": "Whether to use Datasets' streaming mode to load and the data."},
    )
    max_eval_samples: Optional[int] = field(
        default=None,
        metadata={"help": "For debugging purposes, truncate the number of eval examples to this value if set."},
    )
    log_audio: Optional[bool] = field(
        default=False,
        metadata={"help": "For debugging purposes, record the audio samples as well as the ground truths / preds."},
    )
    log_predictions: Optional[bool] = field(
        default=True,
        metadata={"help": "Whether or not to log the ground truths / pred text to the wandb logger."},
    )
    ngram_degree: Optional[int] = field(
        default=5, metadata={"help": "Degree of n-grams used when computing duplicate n-grams in the predicted text."}
    )


def write_metric(summary_writer, eval_metrics, prefix="eval"):
    for metric_name, value in eval_metrics.items():
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/flax/run_pt_long_form_transcription.py [141:229]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class DataTrainingArguments:
    """
    Arguments pertaining to what data we are going to input our model for training and eval.
    """

    dataset_name: str = field(
        default=None,
        metadata={
            "help": "The name of the dataset to use (via the datasets library). Load and combine "
            "multiple datasets by separating dataset hours by a '+' symbol."
        },
    )
    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"},
    )
    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_label_length: int = field(
        default=256,
        metadata={"help": "Truncate transcriptions that are longer `max_label_length` tokens."},
    )
    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"
                " experiment reproducibility and to diff code across experiments in"
                " the UI."
            )
        },
    )
    streaming: bool = field(
        default=True,
        metadata={"help": "Whether to use Datasets' streaming mode to load and the data."},
    )
    max_eval_samples: Optional[int] = field(
        default=None,
        metadata={"help": "For debugging purposes, truncate the number of eval examples to this value if set."},
    )
    log_audio: Optional[bool] = field(
        default=False,
        metadata={"help": "For debugging purposes, record the audio samples as well as the ground truths / preds."},
    )
    log_predictions: Optional[bool] = field(
        default=True,
        metadata={"help": "Whether or not to log the ground truths / pred text to the wandb logger."},
    )
    ngram_degree: Optional[int] = field(
        default=5, metadata={"help": "Degree of n-grams used when computing duplicate n-grams in the predicted text."}
    )


def write_metric(summary_writer, eval_metrics, prefix="eval"):
    for metric_name, value in eval_metrics.items():
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -