8313fc48f53c75cbd9d344ef4836dd7783ab8cb4,data/ted.py,,,#,11

Before Change

parser = argparse.ArgumentParser(description="Processes and downloads TED-LIUMv2 dataset.")
parser.add_argument("--target-dir", default="TEDLIUM_dataset/", type=str, help="Directory to store the dataset.")
parser.add_argument("--tar-path", type=str, help="Path to the TEDLIUM_release tar if downloaded (Optional).")
parser.add_argument("--sample-rate", default=16000, type=int, help="Sample rate")
parser.add_argument("--min-duration", default=1, type=int,
                    help="Prunes training samples shorter than the min duration (given in seconds, default 1)")
parser.add_argument("--max-duration", default=15, type=int,
                    help="Prunes training samples longer than the max duration (given in seconds, default 15)")
args = parser.parse_args()

TED_LIUM_V2_DL_URL = "http://www.openslr.org/resources/19/TEDLIUM_release2.tar.gz"

After Change

from deepspeech_pytorch.data.utils import create_manifest

parser = argparse.ArgumentParser(description="Processes and downloads TED-LIUMv2 dataset.")
parser = add_data_opts(parser)
parser.add_argument("--target-dir", default="TEDLIUM_dataset/", type=str, help="Directory to store the dataset.")
parser.add_argument("--tar-path", type=str, help="Path to the TEDLIUM_release tar if downloaded (Optional).")
args = parser.parse_args()

Instances