def prepare_data()

in normalizer/data_utils.py [0:0]

• 5 lines of code
• 2 McCabe index (conditional complexity)

def prepare_data(dataset):
    # Re-sample to 16kHz and normalise transcriptions
    dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
    dataset = dataset.map(normalize)
    dataset = dataset.filter(is_target_text_in_range, input_columns=["norm_text"])

    return dataset