summaryrefslogtreecommitdiff
path: root/kaldi_decode/local/score.sh
diff options
context:
space:
mode:
authorTed Yin <[email protected]>2015-10-14 15:43:43 +0800
committerTed Yin <[email protected]>2015-10-14 15:43:43 +0800
commitfd2148540efd7a5e5e2c054280d53d3eb3b055cc (patch)
tree47501412a3324e4c13b1238eeb913aae02b2024a /kaldi_decode/local/score.sh
parent0dba4c998fcccb4bae29582b7d8be94de476dd0b (diff)
parentb33b3a6732c6b6a66bd5c44c615be56d66f4ed67 (diff)
Merge pull request #7 from yimmon/master
support kaldi decoder
Diffstat (limited to 'kaldi_decode/local/score.sh')
-rwxr-xr-xkaldi_decode/local/score.sh67
1 files changed, 67 insertions, 0 deletions
diff --git a/kaldi_decode/local/score.sh b/kaldi_decode/local/score.sh
new file mode 100755
index 0000000..b18f350
--- /dev/null
+++ b/kaldi_decode/local/score.sh
@@ -0,0 +1,67 @@
+#!/bin/bash
+# Copyright 2012 Johns Hopkins University (Author: Daniel Povey)
+# Apache 2.0
+
+[ -f ./path.sh ] && . ./path.sh
+
+# begin configuration section.
+cmd=run.pl
+stage=0
+decode_mbr=true
+reverse=false
+word_ins_penalty=0.0
+min_lmwt=5
+max_lmwt=20
+#end configuration section.
+
+[ -f ./path.sh ] && . ./path.sh
+. parse_options.sh || exit 1;
+
+if [ $# -ne 3 ]; then
+ echo "Usage: local/score.sh [--cmd (run.pl|queue.pl...)] <data-dir> <lang-dir|graph-dir> <decode-dir>"
+ echo " Options:"
+ echo " --cmd (run.pl|queue.pl...) # specify how to run the sub-processes."
+ echo " --stage (0|1|2) # start scoring script from part-way through."
+ echo " --decode_mbr (true/false) # maximum bayes risk decoding (confusion network)."
+ echo " --min_lmwt <int> # minumum LM-weight for lattice rescoring "
+ echo " --max_lmwt <int> # maximum LM-weight for lattice rescoring "
+ echo " --reverse (true/false) # score with time reversed features "
+ exit 1;
+fi
+
+data=$1
+lang_or_graph=$2
+dir=$3
+
+symtab=$lang_or_graph/words.txt
+
+for f in $symtab $dir/lat.1.gz $data/text; do
+ [ ! -f $f ] && echo "score.sh: no such file $f" && exit 1;
+done
+
+mkdir -p $dir/scoring/log
+
+cat $data/text | sed 's:<NOISE>::g' | sed 's:<SPOKEN_NOISE>::g' > $dir/scoring/test_filt.txt
+
+$cmd LMWT=$min_lmwt:$max_lmwt $dir/scoring/log/best_path.LMWT.log \
+ lattice-scale --inv-acoustic-scale=LMWT "ark:gunzip -c $dir/lat.*.gz|" ark:- \| \
+ lattice-add-penalty --word-ins-penalty=$word_ins_penalty ark:- ark:- \| \
+ lattice-best-path --word-symbol-table=$symtab \
+ ark:- ark,t:$dir/scoring/LMWT.tra || exit 1;
+
+if $reverse; then
+ for lmwt in `seq $min_lmwt $max_lmwt`; do
+ mv $dir/scoring/$lmwt.tra $dir/scoring/$lmwt.tra.orig
+ awk '{ printf("%s ",$1); for(i=NF; i>1; i--){ printf("%s ",$i); } printf("\n"); }' \
+ <$dir/scoring/$lmwt.tra.orig >$dir/scoring/$lmwt.tra
+ done
+fi
+
+# Note: the double level of quoting for the sed command
+$cmd LMWT=$min_lmwt:$max_lmwt $dir/scoring/log/score.LMWT.log \
+ cat $dir/scoring/LMWT.tra \| \
+ utils/int2sym.pl -f 2- $symtab \| sed 's:\<UNK\>::g' \| \
+ compute-wer --text --mode=present \
+ ark:$dir/scoring/test_filt.txt ark,p:- ">&" $dir/wer_LMWT || exit 1;
+
+exit 0;