嘉渊
2023-05-15 688fb902dd625981060b00788ed70c4c155d2b50
funasr/utils/prepare_data.py
@@ -181,6 +181,11 @@
            ["{}/{}/wav.scp".format(args.data_dir, args.valid_set), data_names[0], data_types[0]],
            ["{}/{}/text".format(args.data_dir, args.valid_set), data_names[1], data_types[1]]
        ]
        if args.embed_path is not None:
            args.train_data_path_and_name_and_type[0].append(
                "{}/embed/kaldi_ark".format(os.path.join(args.embed_path, args.train_set, "embeds.scp")))
            args.valid_data_path_and_name_and_type[0].append(
                "{}/embed/kaldi_ark".format(os.path.join(args.embed_path, args.dev_set, "embeds.scp")))
    else:
        args.train_data_file = os.path.join(args.data_dir, args.train_set, "data.list")
        args.valid_data_file = os.path.join(args.data_dir, args.valid_set, "data.list")