decode_nnet.sh
5.04 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
#!/bin/bash
# Copyright 2012-2013 Karel Vesely, Daniel Povey
# Apache 2.0
# Begin configuration section.
nnet= # Optionally pre-select network to use for getting state-likelihoods
feature_transform= # Optionally pre-select feature transform (in front of nnet)
model= # Optionally pre-select transition model
class_frame_counts= # Optionally pre-select class-counts used to compute PDF priors
stage=0 # stage=1 skips lattice generation
nj=4
cmd=run.pl
max_active=7000 # maximum of active tokens
max_mem=50000000 # limit the fst-size to 50MB (larger fsts are minimized)
beam=13.0 # GMM:13.0
latbeam=8.0 # GMM:6.0
acwt=0.10 # GMM:0.0833, note: only really affects pruning (scoring is on lattices).
scoring_opts="--min-lmwt 4 --max-lmwt 15"
skip_scoring=false
use_gpu_id=-1 # disable gpu
parallel_opts="-pe smp 2" # use 2 CPUs (1 DNN-forward, 1 decoder)
srcdir= # optionaly select dir with DNN model
# End configuration section.
echo "$0 $@" # Print the command line for logging
[ -f ./path.sh ] && . ./path.sh; # source the path.
. parse_options.sh || exit 1;
if [ $# != 3 ]; then
echo "Usage: $0 [options] <graph-dir> <data-dir> <decode-dir>"
echo "... where <decode-dir> is assumed to be a sub-directory of the directory"
echo " where the DNN + transition model is."
echo "e.g.: $0 exp/dnn1/graph_tgpr data/test exp/dnn1/decode_tgpr"
echo ""
echo "This script works on plain or modified features (CMN,delta+delta-delta),"
echo "which are then sent through feature-transform. It works out what type"
echo "of features you used from content of srcdir."
echo ""
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 " --cmd (utils/run.pl|utils/queue.pl <queue opts>) # how to run jobs."
echo ""
echo " --nnet <nnet> # which nnet to use (opt.)"
echo " --feature-transform <nnet> # select transform in front of nnet (opt.)"
echo " --class-frame-counts <file> # file with frame counts (used to compute priors) (opt.)"
echo " --model <model> # which transition model to use (opt.)"
echo ""
echo " --acwt <float> # select acoustic scale for decoding"
echo " --scoring-opts <opts> # options forwarded to local/score.sh"
exit 1;
fi
graphdir=$1
data=$2
dir=$3
[ -z $srcdir ] && srcdir=`dirname $dir`; # Or back-off to: model directory one level up from decoding directory.
sdata=$data/split$nj;
mkdir -p $dir/log
[[ -d $sdata && $data/feats.scp -ot $sdata ]] || split_data.sh $data $nj || exit 1;
echo $nj > $dir/num_jobs
if [ -z "$nnet" ]; then # if --nnet <nnet> was not specified on the command line...
nnet=$srcdir/final.nnet;
fi
[ -z "$nnet" ] && echo "Error nnet '$nnet' does not exist!" && exit 1;
if [ -z "$model" ]; then # if --model <mdl> was not specified on the command line...
model=$srcdir/final.mdl;
fi
# find the feature_transform to use
if [ -z "$feature_transform" ]; then
feature_transform=$srcdir/final.feature_transform
fi
if [ ! -f $feature_transform ]; then
echo "Missing feature_transform '$feature_transform'"
exit 1
fi
# check that files exist
for f in $sdata/1/feats.scp $nnet_i $nnet $model $graphdir/HCLG.fst; do
[ ! -f $f ] && echo "$0: no such file $f" && exit 1;
done
# PREPARE THE LOG-POSTERIOR COMPUTATION PIPELINE
if [ -z "$class_frame_counts" ]; then
class_frame_counts=$srcdir/ali_train_pdf.counts
else
echo "Overriding class_frame_counts by $class_frame_counts"
fi
# Create the feature stream:
feats="ark,s,cs:copy-feats scp:$sdata/JOB/feats.scp ark:- |"
# Optionally add cmvn
if [ -f $srcdir/norm_vars ]; then
norm_vars=$(cat $srcdir/norm_vars 2>/dev/null)
[ ! -f $sdata/1/cmvn.scp ] && echo "$0: cannot find cmvn stats $sdata/1/cmvn.scp" && exit 1
feats="$feats apply-cmvn --norm-vars=$norm_vars --utt2spk=ark:$sdata/JOB/utt2spk scp:$sdata/JOB/cmvn.scp ark:- ark:- |"
fi
# Optionally add deltas
if [ -f $srcdir/delta_order ]; then
delta_order=$(cat $srcdir/delta_order)
feats="$feats add-deltas --delta-order=$delta_order ark:- ark:- |"
fi
# Run the decoding in the queue
if [ $stage -le 0 ]; then
$cmd $parallel_opts JOB=1:$nj $dir/log/decode.JOB.log \
nnet-forward --feature-transform=$feature_transform --no-softmax=true --class-frame-counts=$class_frame_counts --use-gpu-id=$use_gpu_id $nnet "$feats" ark:- \| \
latgen-faster-mapped --max-active=$max_active --max-mem=$max_mem --beam=$beam --lattice-beam=$latbeam \
--acoustic-scale=$acwt --allow-partial=true --word-symbol-table=$graphdir/words.txt \
$model $graphdir/HCLG.fst ark:- "ark:|gzip -c > $dir/lat.JOB.gz" || exit 1;
fi
# Run the scoring
if ! $skip_scoring ; then
[ ! -x local/score.sh ] && \
echo "Not scoring because local/score.sh does not exist or not executable." && exit 1;
local/score.sh $scoring_opts --cmd "$cmd" $data $graphdir $dir || exit 1;
fi
exit 0;