main.py

def main():
    data_root = args.data_root
    os.makedirs(data_root, exist_ok=True)

    target_unpacked_dir = os.path.join(data_root, "CV_unpacked")

    if os.path.exists(target_unpacked_dir):
        logging.info('Find existing folder {}'.format(target_unpacked_dir))
    else:
        logging.info("Could not find Common Voice, Downloading corpus...")

        filename = wget.download(COMMON_VOICE_URL, data_root)
        target_file = os.path.join(data_root, os.path.basename(filename))

        os.makedirs(target_unpacked_dir, exist_ok=True)
        logging.info("Unpacking corpus to {} ...".format(target_unpacked_dir))
        tar = tarfile.open(target_file)
        tar.extractall(target_unpacked_dir)
        tar.close()

    folder_path = os.path.join(target_unpacked_dir, args.version + f'/{args.language}/')

    for csv_file in args.files_to_process:
        data = process_files(
            csv_file=os.path.join(folder_path, csv_file),
            data_root=os.path.join(data_root, os.path.splitext(csv_file)[0]),
            num_workers=args.num_workers
        )
        logging.info('Creating manifests...')
        create_manifest(
            data=data,
            output_name=f'commonvoice_{os.path.splitext(csv_file)[0]}_manifest.json',
            manifest_path=args.manifest_dir,
        )


if __name__ == "__main__":
    main()