Fixed formatting issues in bash scripts.

egs/swbd/ASR/local/eval2000_data_prep.sh

@@ -21,20 +21,19 @@
 # $tdir/reference/hub5e00.english.000405.stm
 
 if [ $# -ne 2 ]; then
-    echo "Usage: "`basename $0`" <speech-dir> <transcription-dir>"
+    echo "Usage: "$(basename $0)" <speech-dir> <transcription-dir>"
     echo "See comments in the script for more details"
     exit 1
 fi
 
 sdir=$1
 tdir=$2
-[ ! -d $sdir/english ] \
+[ ! -d $sdir/english ] &&
-    && echo Expecting directory $sdir/english to be present && exit 1;
+    echo Expecting directory $sdir/english to be present && exit 1
-    [ -d $tdir/2000_hub5_eng_eval_tr ] \
+[ -d $tdir/2000_hub5_eng_eval_tr ] &&
-        && tdir=$tdir/2000_hub5_eng_eval_tr
+    tdir=$tdir/2000_hub5_eng_eval_tr
-            [ ! -d $tdir/reference ] \
+[ ! -d $tdir/reference ] &&
-                && echo Expecting directory $tdir/reference to be present && exit 1;
+    echo Expecting directory $tdir/reference to be present && exit 1
-
 
 dir=data/local/eval2000
 mkdir -p $dir
@@ -44,42 +43,42 @@ tdir=$2
     >$dir/sph.scp
 
 sph2pipe=sph2pipe
-            [ ! -x $sph2pipe ] \
+[ ! -x $sph2pipe ] &&
-                && echo "Could not execute the sph2pipe program at $sph2pipe" && exit 1;
+    echo "Could not execute the sph2pipe program at $sph2pipe" && exit 1
 
 awk -v sph2pipe=$sph2pipe '{
             printf("%s-A %s -f wav -p -c 1 %s |\n", $1, sph2pipe, $2);
             printf("%s-B %s -f wav -p -c 2 %s |\n", $1, sph2pipe, $2);
-        }' < $dir/sph.scp | sort > $dir/wav.scp || exit 1;
+        }' <$dir/sph.scp | sort >$dir/wav.scp || exit 1
 #side A - channel 1, side B - channel 2
 
 # Get segments file...
 # segments file format is: utt-id side-id start-time end-time, e.g.:
 # sw02001-A_000098-001156 sw02001-A 0.98 11.56
 pem=$sdir/english/hub5e_00.pem
-[ ! -f $pem ] && echo "$0: No such file $pem" && exit 1;
+[ ! -f $pem ] && echo "$0: No such file $pem" && exit 1
 # pem file has lines like:
 # en_4156 A unknown_speaker 301.85 302.48
 
 # we ignore the warnings below for now, although they seem to indicate some problems
 # with the data.
-grep -v ';;' $pem \
+grep -v ';;' $pem |
-    | awk '{
+    awk '{
     spk=$1"-"$2;
     utt=sprintf("%s_%06d-%06d",spk,$4*100,$5*100);
-    print utt,spk,$4,$5;}' \
+    print utt,spk,$4,$5;}' |
-        | sort -u | local/extend_segments.pl 0.1 > $dir/segments
+    sort -u | local/extend_segments.pl 0.1 >$dir/segments
 
 # stm file has lines like:
 # en_4156 A en_4156_A 357.64 359.64 <O,en,F,en-F>  HE IS A POLICE OFFICER
 # TODO(arnab): We should really be lowercasing this since the Edinburgh
 # recipe uses lowercase. This is not used in the actual scoring.
-grep -v ';;' $tdir/reference/hub5e00.english.000405.stm \
+grep -v ';;' $tdir/reference/hub5e00.english.000405.stm |
-    | awk '{
+    awk '{
     spk=$1"-"$2;
     utt=sprintf("%s_%06d-%06d",spk,$4*100,$5*100);
-    printf utt; for(n=7;n<=NF;n++) printf(" %s", $n); print ""; }' \
+    printf utt; for(n=7;n<=NF;n++) printf(" %s", $n); print ""; }' |
-        | sort > $dir/text.all
+    sort >$dir/text.all
 
 # We'll use the stm file for sclite scoring.  There seem to be various errors
 # in the stm file that upset hubscr.pl, and we fix them here.
@@ -89,8 +88,8 @@ sed -e 's:((:(:' -e 's:<B_ASIDE>::g' -e 's:<E_ASIDE>::g' \
 
 # next line uses command substitution
 # Just checking that the segments are the same in pem vs. stm.
-! cmp <(awk '{print $1}' $dir/text.all) <(awk '{print $1}' $dir/segments) && \
+! cmp <(awk '{print $1}' $dir/text.all) <(awk '{print $1}' $dir/segments) &&
-    echo "Segments from pem file and stm file do not match." && exit 1;
+    echo "Segments from pem file and stm file do not match." && exit 1
 
 grep -v IGNORE_TIME_SEGMENT_ $dir/text.all >$dir/text
 
@@ -103,11 +102,10 @@ utils/utt2spk_to_spk2utt.pl $dir/utt2spk > $dir/spk2utt
 # awk '{x=$3-0.05; if (x<0.0) x=0.0; y=$4+0.05; print $1, $2, x, y; }' \
 #   $dir/segments.tmp > $dir/segments
 
-awk '{print $1}' $dir/wav.scp \
+awk '{print $1}' $dir/wav.scp |
-    | perl -ane '$_ =~ m:^(\S+)-([AB])$: || die "bad label $_";
+    perl -ane '$_ =~ m:^(\S+)-([AB])$: || die "bad label $_";
     print "$1-$2 $1 $2\n"; ' \
-        > $dir/reco2file_and_channel || exit 1;
+        >$dir/reco2file_and_channel || exit 1
-
 
 echo Data preparation and formatting completed for Eval 2000
 echo "(but not MFCC extraction)"
@@ -116,5 +114,5 @@ awk '{print $1}' $dir/wav.scp \
 
 if [ $(wc -l <$dir/wav.scp) -ne 80 ]; then
     echo "$0: error: expected 80 lines in wav.scp, got $(wc -l <$dir/wav.scp)"
-        exit 1;
+    exit 1
 fi

egs/swbd/ASR/local/rt03_data_prep.sh

@@ -15,10 +15,10 @@ if [ $# -ne 1 ]; then
 fi
 
 sdir=$1
-[ ! -d $sdir/data/audio/eval03/english/cts ] \
+[ ! -d $sdir/data/audio/eval03/english/cts ] &&
-    && echo Expecting directory $sdir/data/audio/eval03/english/cts to be present && exit 1;
+    echo Expecting directory $sdir/data/audio/eval03/english/cts to be present && exit 1
-    [ ! -d $sdir/data/references/eval03/english/cts ] \
+[ ! -d $sdir/data/references/eval03/english/cts ] &&
-        && echo Expecting directory $tdir/data/references/eval03/english/cts to be present && exit 1;
+    echo Expecting directory $tdir/data/references/eval03/english/cts to be present && exit 1
 
 dir=data/local/rt03
 mkdir -p $dir
@@ -32,13 +32,13 @@ sdir=$1
     >$dir/sph.scp
 
 sph2pipe=sph2pipe
-    ! command -v "${sph2pipe}" &> /dev/null \
+! command -v "${sph2pipe}" &>/dev/null &&
-        && echo "Could not execute the sph2pipe program at $sph2pipe" && exit 1;
+    echo "Could not execute the sph2pipe program at $sph2pipe" && exit 1
 
 awk -v sph2pipe=$sph2pipe '{
     printf("%s-A %s -f wav -p -c 1 %s |\n", $1, sph2pipe, $2);
     printf("%s-B %s -f wav -p -c 2 %s |\n", $1, sph2pipe, $2);
-}' < $dir/sph.scp | sort > $dir/wav.scp || exit 1;
+}' <$dir/sph.scp | sort >$dir/wav.scp || exit 1
 #side A - channel 1, side B - channel 2
 
 # Get segments file...
@@ -50,30 +50,30 @@ sdir=$1
 # en_4156 A unknown_speaker 301.85 302.48
 
 #grep -v ';;' $pem \
-cat $tdir/*.stm | grep -v ';;' | grep -v inter_segment_gap \
+cat $tdir/*.stm | grep -v ';;' | grep -v inter_segment_gap |
-    | awk '{
+    awk '{
     spk=$1"-"(($2==1)?"A":"B");
     utt=sprintf("%s_%06d-%06d",spk,$4*100,$5*100);
-    print utt,spk,$4,$5;}' \
+    print utt,spk,$4,$5;}' |
-        | sort -u > $dir/segments
+    sort -u >$dir/segments
 
 # stm file has lines like:
 # en_4156 A en_4156_A 357.64 359.64 <O,en,F,en-F>  HE IS A POLICE OFFICER
 # TODO(arnab): We should really be lowercasing this since the Edinburgh
 # recipe uses lowercase. This is not used in the actual scoring.
 #grep -v ';;' $tdir/reference/hub5e00.english.000405.stm \
-cat $tdir/*.stm | grep -v ';;' | grep -v inter_segment_gap \
+cat $tdir/*.stm | grep -v ';;' | grep -v inter_segment_gap |
-    | awk '{
+    awk '{
     spk=$1"-"(($2==1)?"A":"B");
     utt=sprintf("%s_%06d-%06d",spk,$4*100,$5*100);
-    printf utt; for(n=7;n<=NF;n++) printf(" %s", $n); print ""; }' \
+    printf utt; for(n=7;n<=NF;n++) printf(" %s", $n); print ""; }' |
-        | sort > $dir/text.all
+    sort >$dir/text.all
 
 # We'll use the stm file for sclite scoring.  There seem to be various errors
 # in the stm file that upset hubscr.pl, and we fix them here.
-cat $tdir/*.stm | \
+cat $tdir/*.stm |
-    sed -e 's:((:(:' -e 's:<B_ASIDE>::g' -e 's:<E_ASIDE>::g' | \
+    sed -e 's:((:(:' -e 's:<B_ASIDE>::g' -e 's:<E_ASIDE>::g' |
-    grep -v inter_segment_gap | \
+    grep -v inter_segment_gap |
     awk '{
     printf $1; if ($1==";;") printf(" %s",$2); else printf(($2==1)?" A":" B"); for(n=3;n<=NF;n++) printf(" %s", $n); print ""; }' \
         >$dir/stm
@@ -82,8 +82,8 @@ cat $tdir/*.stm | \
 
 # next line uses command substitution
 # Just checking that the segments are the same in pem vs. stm.
-! cmp <(awk '{print $1}' $dir/text.all) <(awk '{print $1}' $dir/segments) && \
+! cmp <(awk '{print $1}' $dir/text.all) <(awk '{print $1}' $dir/segments) &&
-    echo "Segments from pem file and stm file do not match." && exit 1;
+    echo "Segments from pem file and stm file do not match." && exit 1
 
 grep -v IGNORE_TIME_SEGMENT_ $dir/text.all >$dir/text
 
@@ -96,10 +96,10 @@ utils/utt2spk_to_spk2utt.pl $dir/utt2spk > $dir/spk2utt
 # awk '{x=$3-0.05; if (x<0.0) x=0.0; y=$4+0.05; print $1, $2, x, y; }' \
 #   $dir/segments.tmp > $dir/segments
 
-awk '{print $1}' $dir/wav.scp \
+awk '{print $1}' $dir/wav.scp |
-    | perl -ane '$_ =~ m:^(\S+)-([AB])$: || die "bad label $_";
+    perl -ane '$_ =~ m:^(\S+)-([AB])$: || die "bad label $_";
     print "$1-$2 $1 $2\n"; ' \
-        > $dir/reco2file_and_channel || exit 1;
+        >$dir/reco2file_and_channel || exit 1
 
 ./utils/fix_data_dir.sh $dir
 

egs/swbd/ASR/local/swbd1_data_prep.sh

@@ -17,11 +17,10 @@
 ## will be using "find" to locate this file so we don't make any assumptions
 ## on the directory structure. (Peng Qi, Aug 2014)
 
-
 #check existing directories
 if [ $# != 1 -a $# != 2 ]; then
     echo "Usage: swbd1_data_prep.sh /path/to/SWBD [/path/to/SWBD_DOC]"
-    exit 1;
+    exit 1
 fi
 
 SWBD_DIR=$1
@@ -29,29 +28,27 @@ SWBD_DIR=$1
 dir=data/local/train
 mkdir -p $dir
 
-
 # Audio data directory check
 if [ ! -d $SWBD_DIR ]; then
     echo "Error: run.sh requires a directory argument"
-    exit 1;
+    exit 1
 fi
 
 sph2pipe=sph2pipe
-! command -v "${sph2pipe}" &> /dev/null \
+! command -v "${sph2pipe}" &>/dev/null &&
-    && echo "Could not execute the sph2pipe program at $sph2pipe" && exit 1;
+    echo "Could not execute the sph2pipe program at $sph2pipe" && exit 1
 
 # Option A: SWBD dictionary file check
-[ ! -f ./swb_ms98_transcriptions/sw-ms98-dict.text ] && \
+[ ! -f ./swb_ms98_transcriptions/sw-ms98-dict.text ] &&
-    echo  "SWBD dictionary file does not exist" &&  exit 1;
+    echo "SWBD dictionary file does not exist" && exit 1
 
 # find sph audio files
 find -L $SWBD_DIR -iname '*.sph' | sort >$dir/sph.flist
 
-n=`cat $dir/sph.flist | wc -l`
+n=$(cat $dir/sph.flist | wc -l)
-[ $n -ne 2435 ] && [ $n -ne 2438 ] && \
+[ $n -ne 2435 ] && [ $n -ne 2438 ] &&
     echo Warning: expected 2435 or 2438 data data files, found $n
 
-
 # (1a) Transcriptions preparation
 # make basic transcription file (add segments info)
 # **NOTE: In the default Kaldi recipe, everything is made uppercase, while we
@@ -67,8 +64,8 @@ for(i=4;i<=NF;i++) printf(" %s", $i); printf "\n"
 }' ./swb_ms98_transcriptions/*/*/*-trans.text >$dir/transcripts1.txt
 
 # test if trans. file is sorted
-export LC_ALL=C;
+export LC_ALL=C
-sort -c $dir/transcripts1.txt || exit 1; # check it's sorted.
+sort -c $dir/transcripts1.txt || exit 1 # check it's sorted.
 
 # Remove SILENCE, <B_ASIDE> and <E_ASIDE>.
 
@@ -77,13 +74,12 @@ sort -c $dir/transcripts1.txt || exit 1; # check it's sorted.
 # speech to somone; we will give phones to the other three (NSN, SPN, LAU).
 # There will also be a silence phone, SIL.
 # **NOTE: modified the pattern matches to make them case insensitive
-cat $dir/transcripts1.txt \
+cat $dir/transcripts1.txt |
-    | perl -ane 's:\s\[SILENCE\](\s|$):$1:gi;
+    perl -ane 's:\s\[SILENCE\](\s|$):$1:gi;
     s/<B_ASIDE>//gi;
     s/<E_ASIDE>//gi;
-    print;' \
+    print;' |
-        | awk '{if(NF > 1) { print; } } ' > $dir/transcripts2.txt
+    awk '{if(NF > 1) { print; } } ' >$dir/transcripts2.txt
-
 
 # **NOTE: swbd1_map_words.pl has been modified to make the pattern matches
 # case insensitive
@@ -110,7 +106,7 @@ sed -e 's?.*/??' -e 's?.sph??' $dir/sph.flist | paste - $dir/sph.flist \
 awk -v sph2pipe=$sph2pipe '{
 printf("%s-A %s -f wav -p -c 1 %s |\n", $1, sph2pipe, $2);
 printf("%s-B %s -f wav -p -c 2 %s |\n", $1, sph2pipe, $2);
-}' < $dir/sph.scp | sort > $dir/wav.scp || exit 1;
+}' <$dir/sph.scp | sort >$dir/wav.scp || exit 1
 #side A - channel 1, side B - channel 2
 
 # this file reco2file_and_channel maps recording-id (e.g. sw02001-A)
@@ -118,14 +114,14 @@ printf("%s-B %s -f wav -p -c 2 %s |\n", $1, sph2pipe, $2);
 # sw02001-A  sw02001 A
 # In this case it's trivial, but in other corpora the information might
 # be less obvious.  Later it will be needed for ctm scoring.
-awk '{print $1}' $dir/wav.scp \
+awk '{print $1}' $dir/wav.scp |
-    | perl -ane '$_ =~ m:^(\S+)-([AB])$: || die "bad label $_";
+    perl -ane '$_ =~ m:^(\S+)-([AB])$: || die "bad label $_";
     print "$1-$2 $1 $2\n"; ' \
-        > $dir/reco2file_and_channel || exit 1;
+        >$dir/reco2file_and_channel || exit 1
 
-    awk '{spk=substr($1,1,9); print $1 " " spk}' $dir/segments > $dir/utt2spk \
+awk '{spk=substr($1,1,9); print $1 " " spk}' $dir/segments >$dir/utt2spk ||
-        || exit 1;
+    exit 1
-            sort -k 2 $dir/utt2spk | utils/utt2spk_to_spk2utt.pl > $dir/spk2utt || exit 1;
+sort -k 2 $dir/utt2spk | utils/utt2spk_to_spk2utt.pl >$dir/spk2utt || exit 1
 
 echo Switchboard-1 data preparation succeeded.
 

egs/swbd/ASR/local/swbd1_prepare_dict.sh

@@ -5,9 +5,8 @@
 
 # To be run from one directory above this script.
 
-
 #check existing directories
-[ $# != 0 ] && echo "Usage: local/swbd1_data_prep.sh" && exit 1;
+[ $# != 0 ] && echo "Usage: local/swbd1_data_prep.sh" && exit 1
 
 srcdir=. # This is where we downloaded some stuff..
 dir=./data/local/dict_nosp
@@ -15,20 +14,25 @@ mkdir -p $dir
 srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text
 
 # assume swbd_p1_data_prep.sh was done already.
-[ ! -f "$srcdict" ] && echo "$0: No such file $srcdict" && exit 1;
+[ ! -f "$srcdict" ] && echo "$0: No such file $srcdict" && exit 1
 
-cp $srcdict $dir/lexicon0.txt || exit 1;
+cp $srcdict $dir/lexicon0.txt || exit 1
 chmod a+w $dir/lexicon0.txt
-patch <local/dict.patch $dir/lexicon0.txt || exit 1;
+patch <local/dict.patch $dir/lexicon0.txt || exit 1
 
 #(2a) Dictionary preparation:
 # Pre-processing (remove comments)
-grep -v '^#' $dir/lexicon0.txt | awk 'NF>0' | sort > $dir/lexicon1.txt || exit 1;
+grep -v '^#' $dir/lexicon0.txt | awk 'NF>0' | sort >$dir/lexicon1.txt || exit 1
 
-cat $dir/lexicon1.txt | awk '{ for(n=2;n<=NF;n++){ phones[$n] = 1; }} END{for (p in phones) print p;}' | \
+cat $dir/lexicon1.txt | awk '{ for(n=2;n<=NF;n++){ phones[$n] = 1; }} END{for (p in phones) print p;}' |
-    grep -v sil > $dir/nonsilence_phones.txt  || exit 1;
+    grep -v sil >$dir/nonsilence_phones.txt || exit 1
 
-( echo sil; echo spn; echo nsn; echo lau ) > $dir/silence_phones.txt
+(
+    echo sil
+    echo spn
+    echo nsn
+    echo lau
+) >$dir/silence_phones.txt
 
 echo sil >$dir/optional_silence.txt
 
@@ -41,9 +45,14 @@ cp local/MSU_single_letter.txt $dir/
 # Add single letter lexicon
 # The original swbd lexicon does not have precise single letter lexicion
 # e.g. it does not have entry of W
-( echo '!sil sil'; echo '[vocalized-noise] spn'; echo '[noise] nsn'; \
+(
-    echo '[laughter] lau'; echo '<unk> spn' ) \
+    echo '!sil sil'
-    | cat - $dir/lexicon1.txt $dir/MSU_single_letter.txt  > $dir/lexicon2.txt || exit 1;
+    echo '[vocalized-noise] spn'
+    echo '[noise] nsn'
+    echo '[laughter] lau'
+    echo '<unk> spn'
+) |
+    cat - $dir/lexicon1.txt $dir/MSU_single_letter.txt >$dir/lexicon2.txt || exit 1
 
 # Map the words in the lexicon.  That is-- for each word in the lexicon, we map it
 # to a new written form.  The transformations we do are:
@@ -77,7 +86,7 @@ cp local/MSU_single_letter.txt $dir/
 # in the lexicon.
 
 local/swbd1_map_words.pl -f 1 $dir/lexicon2.txt | sort -u \
-    > $dir/lexicon3.txt || exit 1;
+    >$dir/lexicon3.txt || exit 1
 
 python3 local/format_acronyms_dict.py -i $dir/lexicon3.txt -o $dir/lexicon4.txt \
     -L $dir/MSU_single_letter.txt -M $dir/acronyms_raw.map

egs/swbd/ASR/prepare.sh

@@ -78,8 +78,8 @@ if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
             cp data/local/${x}/text data/local/${x}/text.org
             paste -d "" \
                 <(cut -f 1 -d" " data/local/${x}/text.org) \
-                <(awk '{$1=""; print tolower($0)}' data/local/${x}/text.org | perl -pe 's| \(\%.*\)||g' | perl -pe 's| \<.*\>||g' | sed -e "s/(//g" -e "s/)//g") \
+                <(awk '{$1=""; print tolower($0)}' data/local/${x}/text.org | perl -pe 's| \(\%.*\)||g' | perl -pe 's| \<.*\>||g' | sed -e "s/(//g" -e "s/)//g") |
-                | sed -e 's/\s\+/ /g' > data/local/${x}/text
+                sed -e 's/\s\+/ /g' >data/local/${x}/text
             rm data/local/${x}/text.org
         done