update

嘉渊

2023-07-21 e79c9a801e7e7458ce6894fa85178fa974dfd18b

 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"
@@ -72,25 +72,38 @@
    echo "stage 0: Prepare data for training and inference"
    simu_opts_num_speaker_array=(1 2 3 4)
    simu_opts_sil_scale_array=(2 2 5 9)
    simu_opts_num_speaker=${simu_opts_num_speaker_array[i]}
    simu_opts_sil_scale=${simu_opts_sil_scale_array[i]}
    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}
            dataset=train
        else
            n_mixtures=500
            dataset=dev
        fi
        simu_data_dir=${dset}_ns"$(IFS="n"; echo "${simu_opts_num_speaker_array[*]}")"_beta"$(IFS="n"; echo "${simu_opts_sil_scale_array[*]}")"_${n_mixtures}
        mkdir ${data_dir}/simu/data/${simu_data_dir}/.work
        split_scps=
        for n in $(seq $nj); do
            split_scps="$split_scps ${data_dir}/simu/data/${simu_data_dir}/.work/wav.$n.scp"
        done
        utils/split_scp.pl "${data_dir}/simu/data/${simu_data_dir}/wav.scp" $split_scps || exit 1
        python local/split.py ${data_dir}/simu/data/${simu_data_dir}
#        mkdir -p ${data_dir}/simu/data/${simu_data_dir}/.work
#        split_scps=
#        for n in $(seq $nj); do
#            split_scps="$split_scps ${data_dir}/simu/data/${simu_data_dir}/.work/wav.$n.scp"
#        done
#        utils/split_scp.pl "${data_dir}/simu/data/${simu_data_dir}/wav.scp" $split_scps || exit 1
#        python local/split.py ${data_dir}/simu/data/${simu_data_dir}
#        # 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/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