training/flax/run_eval.py [450:510]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def convert_dataset_str_to_list(
    dataset_names, dataset_config_names, splits=None, text_column_names=None, dataset_hours=None, default_split="train"
):
    if isinstance(dataset_names, str):
        dataset_names = dataset_names.split("+")

        # we assume that all the datasets we're using derive from the distil-whisper org on the Hub - prepend the org name if necessary
        for i in range(len(dataset_names)):
            ds_name = dataset_names[i]
            dataset_names[i] = f"distil-whisper/{ds_name}" if "/" not in ds_name else ds_name

        dataset_config_names = dataset_config_names.split("+")
        splits = splits.split("+") if splits is not None else None
        text_column_names = text_column_names.split("+") if text_column_names is not None else None
        dataset_hours = dataset_hours.split("+") if dataset_hours is not None else None

    # basic checks to ensure we've got the right number of datasets/configs/splits/columns/probs
    if len(dataset_names) != len(dataset_config_names):
        raise ValueError(
            f"Ensure one config is passed for each dataset, got {len(dataset_names)} datasets and"
            f" {len(dataset_config_names)} configs."
        )

    if splits is not None and len(splits) != len(dataset_names):
        raise ValueError(
            f"Ensure one split is passed for each dataset, got {len(dataset_names)} datasets and {len(splits)} splits."
        )

    if text_column_names is not None and len(text_column_names) != len(dataset_names):
        raise ValueError(
            f"Ensure one text column name is passed for each dataset, got {len(dataset_names)} datasets and"
            f" {len(text_column_names)} text column names."
        )

    if dataset_hours is not None:
        if len(dataset_hours) != len(dataset_names):
            raise ValueError(
                f"Ensure one probability is passed for each dataset, got {len(dataset_names)} datasets and "
                f"{len(dataset_hours)} hours."
            )
        dataset_hours = [float(ds_hours) for ds_hours in dataset_hours]
    else:
        dataset_hours = [None] * len(dataset_names)

    text_column_names = (
        text_column_names if text_column_names is not None else ["text" for _ in range(len(dataset_names))]
    )
    splits = splits if splits is not None else [default_split for _ in range(len(dataset_names))]

    dataset_names_dict = []
    for i, ds_name in enumerate(dataset_names):
        dataset_names_dict.append(
            {
                "name": ds_name,
                "config": dataset_config_names[i],
                "split": splits[i],
                "text_column_name": text_column_names[i],
                "hours": dataset_hours[i],
            }
        )
    return dataset_names_dict
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/flax/run_speed_pt.py [251:311]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def convert_dataset_str_to_list(
    dataset_names, dataset_config_names, splits=None, text_column_names=None, dataset_hours=None, default_split="train"
):
    if isinstance(dataset_names, str):
        dataset_names = dataset_names.split("+")

        # we assume that all the datasets we're using derive from the distil-whisper org on the Hub - prepend the org name if necessary
        for i in range(len(dataset_names)):
            ds_name = dataset_names[i]
            dataset_names[i] = f"distil-whisper/{ds_name}" if "/" not in ds_name else ds_name

        dataset_config_names = dataset_config_names.split("+")
        splits = splits.split("+") if splits is not None else None
        text_column_names = text_column_names.split("+") if text_column_names is not None else None
        dataset_hours = dataset_hours.split("+") if dataset_hours is not None else None

    # basic checks to ensure we've got the right number of datasets/configs/splits/columns/probs
    if len(dataset_names) != len(dataset_config_names):
        raise ValueError(
            f"Ensure one config is passed for each dataset, got {len(dataset_names)} datasets and"
            f" {len(dataset_config_names)} configs."
        )

    if splits is not None and len(splits) != len(dataset_names):
        raise ValueError(
            f"Ensure one split is passed for each dataset, got {len(dataset_names)} datasets and {len(splits)} splits."
        )

    if text_column_names is not None and len(text_column_names) != len(dataset_names):
        raise ValueError(
            f"Ensure one text column name is passed for each dataset, got {len(dataset_names)} datasets and"
            f" {len(text_column_names)} text column names."
        )

    if dataset_hours is not None:
        if len(dataset_hours) != len(dataset_names):
            raise ValueError(
                f"Ensure one probability is passed for each dataset, got {len(dataset_names)} datasets and "
                f"{len(dataset_hours)} hours."
            )
        dataset_hours = [float(ds_hours) for ds_hours in dataset_hours]
    else:
        dataset_hours = [None] * len(dataset_names)

    text_column_names = (
        text_column_names if text_column_names is not None else ["text" for _ in range(len(dataset_names))]
    )
    splits = splits if splits is not None else [default_split for _ in range(len(dataset_names))]

    dataset_names_dict = []
    for i, ds_name in enumerate(dataset_names):
        dataset_names_dict.append(
            {
                "name": ds_name,
                "config": dataset_config_names[i],
                "split": splits[i],
                "text_column_name": text_column_names[i],
                "hours": dataset_hours[i],
            }
        )
    return dataset_names_dict
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -