Skip to content

Fix the gawk-specific feature problems in prepare dict scripts. #1147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danpovey merged 4 commits into from
Oct 27, 2016
Merged

Fix the gawk-specific feature problems in prepare dict scripts. #1147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f60300f
Fix gawk-specific features problem in prepare dict scripts
Oct 27, 2016
6937f79
Fix gawk-specific features problem in prepare dict scripts
Oct 27, 2016
ac0bde8
Correct upper to lower case in dict preparation scripts
Oct 27, 2016
e938c69
Remove useless comments(upper-case)
Oct 27, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions egs/aspire/s5/local/fisher_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,7 @@ srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=toupper($0); print}' \
$srcdict | sort | awk '($0 !~ /^[:space:]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;

grep -v '^#' $srcdict | tr '[a-z]' '[A-Z]' | 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;}' | \
grep -v SIL > $dir/nonsilence_phones.txt || exit 1;
Expand Down
5 changes: 1 addition & 4 deletions egs/fisher_english/s5/local/fisher_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,7 @@ srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=toupper($0); print}' \
$srcdict | sort | awk '($0 !~ /^[:space:]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;

grep -v '^#' $srcdict | tr '[a-z]' '[A-Z]' | 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;}' | \
grep -v SIL > $dir/nonsilence_phones.txt || exit 1;
Expand Down
7 changes: 2 additions & 5 deletions egs/fisher_swbd/s5/local/fisher_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,11 +116,8 @@ cp $srcdict $dir/lexicon0.txt || exit 1;
patch <local/dict.patch $dir/lexicon0.txt || exit 1;

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {print}' \
$dir/lexicon0.txt | sort | awk '($0 !~ /^[[:space:]]*$/) {print}' \
> $dir/lexicon1_swbd.txt || exit 1;

# Pre-processing (remove comments)
grep -v '^#' $dir/lexicon0.txt | awk 'NF>0' | sort > $dir/lexicon1_swbd.txt || exit 1;

cat $dir/lexicon1_swbd.txt | awk '{ for(n=2;n<=NF;n++){ phones[$n] = 1; }} END{for (p in phones) print p;}' | \
grep -v SIL > $dir/nonsilence_phones_msu.txt || exit 1;
Expand Down
7 changes: 2 additions & 5 deletions egs/fisher_swbd/s5/local/fisher_swbd_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,11 +116,8 @@ cp $srcdict $dir/lexicon0.txt || exit 1;
patch <local/dict.patch $dir/lexicon0.txt || exit 1;

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {print}' \
$dir/lexicon0.txt | sort | awk '($0 !~ /^[[:space:]]*$/) {print}' \
> $dir/lexicon1_swbd.txt || exit 1;

# Pre-processing (remove comments)
grep -v '^#' $dir/lexicon0.txt | awk 'NF>0' | sort > $dir/lexicon1_swbd.txt || exit 1;

cat $dir/lexicon1_swbd.txt | awk '{ for(n=2;n<=NF;n++){ phones[$n] = 1; }} END{for (p in phones) print p;}' | \
grep -v SIL > $dir/nonsilence_phones_msu.txt || exit 1;
Expand Down
7 changes: 2 additions & 5 deletions egs/fisher_swbd/s5/local/swbd1_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,11 +19,8 @@ srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text
[ ! -f "$srcdict" ] && echo "No such file $srcdict" && exit 1;

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=tolower($0); print}' \
$srcdict | sort | awk '($0 !~ /^[:space:]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;

# Pre-processing (Lower-case, remove comments)
grep -v '^#' $srcdict | tr '[A-Z]' '[a-z]' | 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;}' | \
grep -v sil > $dir/nonsilence_phones.txt || exit 1;
Expand Down
5 changes: 1 addition & 4 deletions egs/sre10/v1/local/dnn/fisher_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,7 @@ srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=toupper($0); print}' \
$srcdict | sort | awk '($0 !~ /^[:space:]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;

grep -v '^#' $srcdict | tr '[a-z]' '[A-Z]' | 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;}' | \
grep -v SIL > $dir/nonsilence_phones.txt || exit 1;
Expand Down
7 changes: 2 additions & 5 deletions egs/swbd/s5/local/swbd1_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,11 +19,8 @@ srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text
[ ! -f "$srcdict" ] && echo "No such file $srcdict" && exit 1;

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=tolower($0); print}' \
$srcdict | sort | awk '($0 !~ /^[[:space:]]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;

# Pre-processing (Lower-case, remove comments)
grep -v '^#' $srcdict | tr '[A-Z]' '[a-z]' | 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;}' | \
grep -v sil > $dir/nonsilence_phones.txt || exit 1;
Expand Down
5 changes: 1 addition & 4 deletions egs/swbd/s5/local/swbd_p1_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,10 +25,7 @@ srcdict=$srcdir/swb_ms98_transcriptions/sw-ms98-dict.text

#(2a) Dictionary preparation:
# Pre-processing (Upper-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=toupper($0); print}' \
$srcdict | sort | awk '($0 !~ /^[:space:]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;

grep -v '^#' $srcdict | tr '[a-z]' '[A-Z]' | 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;}' | \
grep -v SIL > $dir/nonsilence_phones.txt || exit 1;
Expand Down
4 changes: 1 addition & 3 deletions egs/swbd/s5b/local/swbd1_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,7 @@ patch <local/dict.patch $dir/lexicon0.txt || exit 1;

#(2a) Dictionary preparation:
# Pre-processing (lower-case, remove comments)
awk 'BEGIN{getline}($0 !~ /^#/) {$0=tolower($0); print}' \
$srcdict | sort | awk '($0 !~ /^[[:space:]]*$/) {print}' \
> $dir/lexicon1.txt || exit 1;
grep -v '^#' $srcdict | tr '[A-Z]' '[a-z]' | 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;}' | \
Expand Down
3 changes: 1 addition & 2 deletions egs/swbd/s5c/local/swbd1_prepare_dict.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,10 +22,9 @@ cp $srcdict $dir/lexicon0.txt || exit 1;
patch <local/dict.patch $dir/lexicon0.txt || exit 1;

#(2a) Dictionary preparation:
# Pre-processing (remove comments, remove empty lines)
# Pre-processing (remove comments)
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;}' | \
grep -v sil > $dir/nonsilence_phones.txt || exit 1;

Expand Down