[egs] Fixed some issues in the multilingual BABEL example scripts (#1850)

[processor-sdk/kaldi.git] / egs / wsj / s5 / steps / nnet3 / decode.sh

diff --git a/egs/wsj/s5/steps/nnet3/decode.sh b/egs/wsj/s5/steps/nnet3/decode.sh
index 151dd6be2e7c8e363a8dca80b6341f42af6ac77b..0484fd229a60c72336cbb89e631ccbc2de9e2168 100755 (executable)
--- a/egs/wsj/s5/steps/nnet3/decode.sh
+++ b/egs/wsj/s5/steps/nnet3/decode.sh
@@ -23,14 +23,13 @@ ivector_scale=1.0
 lattice_beam=8.0 # Beam we use in lattice generation.
 iter=final
 num_threads=1 # if >1, will use gmm-latgen-faster-parallel
-parallel_opts=  # ignored now.
 scoring_opts=
+skip_diagnostics=false
 skip_scoring=false
 extra_left_context=0
 extra_right_context=0
 extra_left_context_initial=-1
 extra_right_context_final=-1
-feat_type=
 online_ivector_dir=
 minimize=false
 # End configuration section.
@@ -55,7 +54,6 @@ if [ $# -ne 3 ]; then
   echo "  --iter <iter>                            # Iteration of model to decode; default is final."
   echo "  --scoring-opts <string>                  # options to local/score.sh"
   echo "  --num-threads <n>                        # number of threads to use, default 1."
-  echo "  --parallel-opts <opts>                   # e.g. '--num-threads 4' if you supply --num-threads 4"
   exit 1;
 fi
 
@@ -66,8 +64,11 @@ srcdir=`dirname $dir`; # Assume model directory one level up from decoding direc
 model=$srcdir/$iter.mdl
 
 
-[ ! -z "$online_ivector_dir" ] && \
+extra_files=
+if [ ! -z "$online_ivector_dir" ]; then
+  steps/nnet2/check_ivectors_compatible.sh $srcdir $online_ivector_dir || exit 1
   extra_files="$online_ivector_dir/ivector_online.scp $online_ivector_dir/ivector_period"
+fi
 
 for f in $graphdir/HCLG.fst $data/feats.scp $model $extra_files; do
   [ ! -f $f ] && echo "$0: no such file $f" && exit 1;
@@ -84,45 +85,27 @@ echo $nj > $dir/num_jobs
 
 
 ## Set up features.
-if [ -z "$feat_type" ]; then
-  if [ -f $srcdir/final.mat ]; then feat_type=lda; else feat_type=raw; fi
-  echo "$0: feature type is $feat_type"
-fi
-
-splice_opts=`cat $srcdir/splice_opts 2>/dev/null`
+echo "$0: feature type is raw"
 
-case $feat_type in
-  raw) feats="ark,s,cs:apply-cmvn $cmvn_opts --utt2spk=ark:$sdata/JOB/utt2spk scp:$sdata/JOB/cmvn.scp scp:$sdata/JOB/feats.scp ark:- |";;
-  lda) feats="ark,s,cs:apply-cmvn $cmvn_opts --utt2spk=ark:$sdata/JOB/utt2spk scp:$sdata/JOB/cmvn.scp scp:$sdata/JOB/feats.scp ark:- | splice-feats $splice_opts ark:- ark:- | transform-feats $srcdir/final.mat ark:- ark:- |"
-    ;;
-  *) echo "$0: invalid feature type $feat_type" && exit 1;
-esac
+feats="ark,s,cs:apply-cmvn $cmvn_opts --utt2spk=ark:$sdata/JOB/utt2spk scp:$sdata/JOB/cmvn.scp scp:$sdata/JOB/feats.scp ark:- |"
 if [ ! -z "$transform_dir" ]; then
   echo "$0: using transforms from $transform_dir"
   [ ! -s $transform_dir/num_jobs ] && \
     echo "$0: expected $transform_dir/num_jobs to contain the number of jobs." && exit 1;
   nj_orig=$(cat $transform_dir/num_jobs)
 
-  if [ $feat_type == "raw" ]; then trans=raw_trans;
-  else trans=trans; fi
-  if [ $feat_type == "lda" ] && \
-    ! cmp $transform_dir/../final.mat $srcdir/final.mat && \
-    ! cmp $transform_dir/final.mat $srcdir/final.mat; then
-    echo "$0: LDA transforms differ between $srcdir and $transform_dir"
-    exit 1;
-  fi
-  if [ ! -f $transform_dir/$trans.1 ]; then
-    echo "$0: expected $transform_dir/$trans.1 to exist (--transform-dir option)"
+  if [ ! -f $transform_dir/raw_trans.1 ]; then
+    echo "$0: expected $transform_dir/raw_trans.1 to exist (--transform-dir option)"
     exit 1;
   fi
   if [ $nj -ne $nj_orig ]; then
     # Copy the transforms into an archive with an index.
-    for n in $(seq $nj_orig); do cat $transform_dir/$trans.$n; done | \
-       copy-feats ark:- ark,scp:$dir/$trans.ark,$dir/$trans.scp || exit 1;
-    feats="$feats transform-feats --utt2spk=ark:$sdata/JOB/utt2spk scp:$dir/$trans.scp ark:- ark:- |"
+    for n in $(seq $nj_orig); do cat $transform_dir/raw_trans.$n; done | \
+       copy-feats ark:- ark,scp:$dir/raw_trans.ark,$dir/raw_trans.scp || exit 1;
+    feats="$feats transform-feats --utt2spk=ark:$sdata/JOB/utt2spk scp:$dir/raw_trans.scp ark:- ark:- |"
   else
     # number of jobs matches with alignment dir.
-    feats="$feats transform-feats --utt2spk=ark:$sdata/JOB/utt2spk ark:$transform_dir/$trans.JOB ark:- ark:- |"
+    feats="$feats transform-feats --utt2spk=ark:$sdata/JOB/utt2spk ark:$transform_dir/raw_trans.JOB ark:- ark:- |"
   fi
 elif grep 'transform-feats --utt2spk' $srcdir/log/train.1.log >&/dev/null; then
   echo "$0: **WARNING**: you seem to be using a neural net system trained with transforms,"
@@ -161,11 +144,18 @@ if [ $stage -le 1 ]; then
      $graphdir/HCLG.fst "$feats" "$lat_wspecifier" || exit 1;
 fi
 
-# The output of this script is the files "lat.*.gz"-- we'll rescore this at
-# different acoustic scales to get the final output.
-
 
 if [ $stage -le 2 ]; then
+  if ! $skip_diagnostics ; then
+    [ ! -z $iter ] && iter_opt="--iter $iter"
+    steps/diagnostic/analyze_lats.sh --cmd "$cmd" $iter_opt $graphdir $dir
+  fi
+fi
+
+
+# The output of this script is the files "lat.*.gz"-- we'll rescore this at
+# different acoustic scales to get the final output.
+if [ $stage -le 3 ]; then
   if ! $skip_scoring ; then
     [ ! -x local/score.sh ] && \
       echo "Not scoring because local/score.sh does not exist or not executable." && exit 1;