#!/bin/bash
  # Copyright 2012-2013  Johns Hopkins University (Author: Daniel Povey)
  # Apache 2.0
  
  # Computes training alignments; assumes features are (LDA+MLLT or delta+delta-delta)
  # + fMLLR (probably with SAT models).
  # It first computes an alignment with the final.alimdl (or the final.mdl if final.alimdl
  # is not present), then does 2 iterations of fMLLR estimation.
  
  # If you supply the --use-graphs option, it will use the training
  # graphs from the source directory (where the model is).  In this
  # case the number of jobs must match the source directory.
  
  
  # Begin configuration section.
  stage=0
  nj=4
  cmd=run.pl
  use_graphs=false
  # Begin configuration.
  scale_opts="--transition-scale=1.0 --acoustic-scale=0.1 --self-loop-scale=0.1"
  beam=10
  retry_beam=40
  boost_silence=1.0 # factor by which to boost silence during alignment.
  # End configuration options.
  
  echo "$0 $@"  # Print the command line for logging
  
  [ -f path.sh ] && . ./path.sh # source the path.
  . parse_options.sh || exit 1;
  
  if [ $# != 4 ]; then
     echo "usage: steps/align_fmllr.sh <data-dir> <lang-dir> <src-dir> <align-dir>"
     echo "e.g.:  steps/align_fmllr.sh data/train data/lang exp/tri1 exp/tri1_ali"
     echo "main options (for others, see top of script file)"
     echo "  --config <config-file>                           # config containing options"
     echo "  --nj <nj>                                        # number of parallel jobs"
     echo "  --use-graphs true                                # use graphs in src-dir"
     echo "  --cmd (utils/run.pl|utils/queue.pl <queue opts>) # how to run jobs."
     exit 1;
  fi
  
  data=$1
  lang=$2
  srcdir=$3
  dir=$4
  
  oov=`cat $lang/oov.int` || exit 1;
  silphonelist=`cat $lang/phones/silence.csl` || exit 1;
  sdata=$data/split$nj
  
  mkdir -p $dir/log
  echo $nj > $dir/num_jobs
  [[ -d $sdata && $data/feats.scp -ot $sdata ]] || split_data.sh $data $nj || exit 1;
  
  utils/lang/check_phones_compatible.sh $lang/phones.txt $srcdir/phones.txt || exit 1;
  cp $lang/phones.txt $dir || exit 1;
  
  cp $srcdir/{tree,final.mdl} $dir || exit 1;
  cp $srcdir/final.occs $dir;
  splice_opts=`cat $srcdir/splice_opts 2>/dev/null` # frame-splicing options.
  cp $srcdir/splice_opts $dir 2>/dev/null # frame-splicing options.
  cmvn_opts=`cat $srcdir/cmvn_opts 2>/dev/null`
  cp $srcdir/cmvn_opts $dir 2>/dev/null # cmn/cmvn option.
  
  if [[ ! -f $srcdir/final.mat || ! -f $srcdir/full.mat ]]; then
    echo "$0: we require final.mat and full.mat in the source directory $srcdir"
  fi
  
  full_lda_mat="get-full-lda-mat --print-args=false $srcdir/final.mat $srcdir/full.mat -|"
  cp $srcdir/full.mat $srcdir/final.mat $dir
  
  raw_dim=$(feat-to-dim scp:$data/feats.scp -) || exit 1;
  ! [ "$raw_dim" -gt 0 ] && echo "raw feature dim not set" && exit 1;
  
  splicedfeats="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 $splice_opts ark:- ark:- |"
  sifeats="$splicedfeats transform-feats $srcdir/final.mat ark:- ark:- |"
  
  ## Set up model and alignment model.
  mdl=$srcdir/final.mdl
  if [ -f $srcdir/final.alimdl ]; then
    alimdl=$srcdir/final.alimdl
  else
    alimdl=$srcdir/final.mdl
  fi
  [ ! -f $mdl ] && echo "$0: no such model $mdl" && exit 1;
  alimdl_cmd="gmm-boost-silence --boost=$boost_silence `cat $lang/phones/optional_silence.csl` $alimdl - |"
  mdl_cmd="gmm-boost-silence --boost=$boost_silence `cat $lang/phones/optional_silence.csl` $mdl - |"
  
  
  ## Work out where we're getting the graphs from.
  if $use_graphs; then
    [ "$nj" != "`cat $srcdir/num_jobs`" ] && \
      echo "$0: you specified --use-graphs true, but #jobs mismatch." && exit 1;
    [ ! -f $srcdir/fsts.1.gz ] && echo "No graphs in $srcdir" && exit 1;
    graphdir=$srcdir
  else
    graphdir=$dir
    if [ $stage -le 0 ]; then
      echo "$0: compiling training graphs"
      tra="ark:utils/sym2int.pl --map-oov $oov -f 2- $lang/words.txt $sdata/JOB/text|";
      $cmd JOB=1:$nj $dir/log/compile_graphs.JOB.log  \
        compile-train-graphs --read-disambig-syms=$lang/phones/disambig.int $dir/tree $dir/final.mdl  $lang/L.fst "$tra" \
          "ark:|gzip -c >$dir/fsts.JOB.gz" || exit 1;
    fi
  fi
  
  
  if [ $stage -le 1 ]; then
    echo "$0: aligning data in $data using $alimdl and speaker-independent features."
    $cmd JOB=1:$nj $dir/log/align_pass1.JOB.log \
      gmm-align-compiled $scale_opts --beam=$beam --retry-beam=$retry_beam "$alimdl_cmd" \
      "ark:gunzip -c $graphdir/fsts.JOB.gz|" "$sifeats" "ark:|gzip -c >$dir/pre_ali.JOB.gz" || exit 1;
  fi
  
  if [ $stage -le 2 ]; then
    echo "$0: computing fMLLR transforms"
    if [ "$alimdl" != "$mdl" ]; then
      $cmd JOB=1:$nj $dir/log/fmllr.JOB.log \
        ali-to-post "ark:gunzip -c $dir/pre_ali.JOB.gz|" ark:- \| \
        weight-silence-post 0.0 $silphonelist $alimdl ark:- ark:- \| \
        gmm-post-to-gpost $alimdl "$sifeats" ark:- ark:- \| \
        gmm-est-fmllr-raw-gpost --raw-feat-dim=$raw_dim --spk2utt=ark:$sdata/JOB/spk2utt \
         $mdl "$full_lda_mat" "$splicedfeats" ark,s,cs:- ark:$dir/raw_trans.JOB || exit 1;
    else
      $cmd JOB=1:$nj $dir/log/fmllr.JOB.log \
        ali-to-post "ark:gunzip -c $dir/pre_ali.JOB.gz|" ark:- \| \
        weight-silence-post 0.0 $silphonelist $alimdl ark:- ark:- \| \
        gmm-est-fmllr-raw --raw-feat-dim=$raw_dim --spk2utt=ark:$sdata/JOB/spk2utt $mdl "$full_lda_mat" \
         "$splicedfeats" ark,s,cs:- ark:$dir/raw_trans.JOB || exit 1;
    fi
  fi
  
  feats="ark,s,cs:apply-cmvn $cmvn_opts --utt2spk=ark:$sdata/JOB/utt2spk scp:$sdata/JOB/cmvn.scp scp:$sdata/JOB/feats.scp ark:- | transform-feats --utt2spk=ark:$sdata/JOB/utt2spk ark:$dir/raw_trans.JOB ark:- ark:- | splice-feats $splice_opts ark:- ark:- | transform-feats $srcdir/final.mat ark:- ark:- |"
  
  if [ $stage -le 3 ]; then
    echo "$0: doing final alignment."
    $cmd JOB=1:$nj $dir/log/align_pass2.JOB.log \
      gmm-align-compiled $scale_opts --beam=$beam --retry-beam=$retry_beam "$mdl_cmd" \
      "ark:gunzip -c $graphdir/fsts.JOB.gz|" "$feats" "ark:|gzip -c >$dir/ali.JOB.gz" || exit 1;
  fi
  
  rm $dir/pre_ali.*.gz
  
  echo "$0: done aligning data."
  
  steps/diagnostic/analyze_alignments.sh --cmd "$cmd" $lang $dir
  
  utils/summarize_warnings.pl $dir/log
  
  exit 0;