update

嘉渊

2023-07-21 d273f7e12693e5b366cbf2ff7d01dde0264b01d9

update

 egs/callhome/eend_ola/local/gen_feats_scp.py

@@ -9,19 +9,17 @@
    args = parser.parse_args()
    root_path = args.root_path
    out_path = args.out_path
    datasets = ["train", "dev"]
    split_num = args.split_num

    for dataset in datasets:
        with open(os.path.join(out_path, dataset, "feats.scp"), "w") as out_f:
            for i in range(split_num):
                idx = str(i + 1)
                feature_file = os.path.join(root_path, dataset, "feature.scp.{}".format(idx))
                label_file = os.path.join(root_path, dataset, "label.scp.{}".format(idx))
                with open(feature_file) as ff, open(label_file) as fl:
                    ff_lines = ff.readlines()
                    fl_lines = fl.readlines()
                    for ff_line, fl_line in zip(ff_lines, fl_lines):
                        sample_name, f_path = ff_line.strip().split()
                        _, l_path = fl_line.strip().split()
                        out_f.write("{} {} {}\n".format(sample_name, f_path, l_path))
    with open(os.path.join(out_path, "feats.scp"), "w") as out_f:
        for i in range(split_num):
            idx = str(i + 1)
            feature_file = os.path.join(root_path, "feature.scp.{}".format(idx))
            label_file = os.path.join(root_path, "label.scp.{}".format(idx))
            with open(feature_file) as ff, open(label_file) as fl:
                ff_lines = ff.readlines()
                fl_lines = fl.readlines()
                for ff_line, fl_line in zip(ff_lines, fl_lines):
                    sample_name, f_path = ff_line.strip().split()
                    _, l_path = fl_line.strip().split()
                    out_f.write("{} {} {}\n".format(sample_name, f_path, l_path))

 egs/callhome/eend_ola/run_test.sh

@@ -101,8 +101,8 @@
#              --index JOB
        mkdir -p ${data_dir}/ark_data/dump/simu_data/data/$dataset
        python local/gen_feats_scp.py \
              --root_path ${data_dir}/ark_data/dump/simu_data \
              --out_path ${data_dir}/ark_data/dump/simu_data/data \
              --root_path ${data_dir}/ark_data/dump/simu_data/$dataset \
              --out_path ${data_dir}/ark_data/dump/simu_data/data/$dataset \
              --split_num $nj
    done
fi