extract_language_lst.sh 638 Bytes
DATADIR="data"
OUTDIR="exp/kmeans_euclidian/ivectors"
NEW_LSTDIR="${OUTDIR}/lst"

TRAIN_LST=${DATADIR}/pvectors_1rst/lst/train_${kfold}.lst
VAL_LST=${DATADIR}/pvectors_1rst/lst/val_${kfold}.lst
TRAIN_LANG_LST=${NEW_LSTDIR}/train_${kfold}_lang.lst
VAL_LANG_LST=${NEW_LSTDIR}/val_${kfold}_lang.lst
METAS_LANG=${NEW_LSTDIR}/metas_${kfold}_lang.lst
     

awk '$2=$1' FS=, OFS=, ${TRAIN_LST} > ${TRAIN_LANG_LST}
echo "VAL EXTRACT LANGUAGE INFO DONE"
awk '$2=$1' FS=, OFS=, ${VAL_LST} > ${VAL_LANG_LST}
echo "TRAIN EXTRACT LANGUAGE INFO DONE"
cat "${TRAIN_LANG_LST}" "${VAL_LANG_LST}" > "${METAS_LANG}"
echo "GLOBAL EXTRACT LANGUAGE INFO DONE"