update

嘉渊

2023-07-21 5f3f194ffd459fd5ebe6ea46da5e532820a66060

update

 egs/callhome/eend_ola/local/gen_feats_scp.py

New file
@@ -0,0 +1,27 @@
import os
import argparse

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument("--root_path", type=str)
    parser.add_argument("--out_path", type=str)
    parser.add_argument("--split_num", type=int, default=64)
    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))

 egs/callhome/eend_ola/run_test.sh

@@ -12,7 +12,7 @@
nj=64

# feature configuration
data_dir="/nfs/wangjiaming.wjm/EEND_DATA_sad30_snr10n15n20/convert_chunk2000/data"
data_dir="/nfs/wangjiaming.wjm/EEND_DATA_sad30_snr10n15n20/convert_test/data"
simu_feats_dir="/nfs/wangjiaming.wjm/EEND_ARK_DATA/dump/simu_data/data"
simu_feats_dir_chunk2000="/nfs/wangjiaming.wjm/EEND_ARK_DATA/dump/simu_data_chunk2000/data"
callhome_feats_dir_chunk2000="/nfs/wangjiaming.wjm/EEND_ARK_DATA/dump/callhome_chunk2000/data"
@@ -74,7 +74,7 @@
    simu_opts_sil_scale_array=(2 2 5 9)
    simu_opts_num_train=100000

    # for simulated data of chunk500
    # for simulated data of chunk500 and chunk2000
    for dset in swb_sre_tr swb_sre_cv; do
        if [ "$dset" == "swb_sre_tr" ]; then
            n_mixtures=${simu_opts_num_train}
@@ -91,13 +91,19 @@
#        done
#        utils/split_scp.pl "${data_dir}/simu/data/${simu_data_dir}/wav.scp" $split_scps || exit 1
#        python local/split.py ${data_dir}/simu/data/${simu_data_dir}
        output_dir=${data_dir}/ark_data/dump/simu_data/$dataset
        mkdir -p $output_dir/.logs
        $dump_cmd --max-jobs-run $nj JOB=1:$nj $output_dir/.logs/dump.JOB.log \
        python local/dump_feature.py \
              --data_dir ${data_dir}/simu/data/${simu_data_dir}/.work \
              --output_dir ${data_dir}/ark_data/dump/simu_data/$dataset \
              --index JOB
#        # for chunk_size=500
#        output_dir=${data_dir}/ark_data/dump/simu_data/$dataset
#        mkdir -p $output_dir/.logs
#        $dump_cmd --max-jobs-run $nj JOB=1:$nj $output_dir/.logs/dump.JOB.log \
#        python local/dump_feature.py \
#              --data_dir ${data_dir}/simu/data/${simu_data_dir}/.work \
#              --output_dir ${data_dir}/ark_data/dump/simu_data/$dataset \
#              --index JOB
        mkdir -p ${data_dir}/ark_data/dump/simu_data/data/$dataset
        python local_rank/gen_feats_scp.py \
              --root_path ${data_dir}/ark_data/dump/simu_data \
              --out_path ${data_dir}/ark_data/dump/simu_data/data/$dataset \
              --split_num $nj
    done
fi