compare_wer.sh
1.89 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
#!/bin/bash
# this script is used for comparing decoding results between systems.
# e.g. local/chain/compare_wer.sh exp/chain/cnn{1a,1b}
# ./local/chain/compare_wer.sh exp/chain/cnn1a
# System cnn1a
# WER 0.61
# CER 0.15
# Final train prob -0.0377
# Final valid prob -0.0380
# Final train prob (xent) -0.0830
# Final valid prob (xent) -0.0838
if [ $# == 0 ]; then
echo "Usage: $0: <dir1> [<dir2> ... ]"
echo "e.g.: $0 exp/chain/cnn{1a,1b}"
exit 1
fi
echo "# $0 $*"
used_epochs=false
echo -n "# System "
for x in $*; do printf "% 10s" " $(basename $x)"; done
echo
echo -n "# WER "
for x in $*; do
wer=$(cat $x/decode_test/scoring_kaldi/best_wer | awk '{print $2}')
printf "% 10s" $wer
done
echo
echo -n "# CER "
for x in $*; do
cer=$(cat $x/decode_test/scoring_kaldi/best_cer | awk '{print $2}')
printf "% 10s" $cer
done
echo
if $used_epochs; then
exit 0; # the diagnostics aren't comparable between regular and discriminatively trained systems.
fi
echo -n "# Final train prob "
for x in $*; do
prob=$(grep Overall $x/log/compute_prob_train.final.log | grep -v xent | awk '{printf("%.4f", $8)}')
printf "% 10s" $prob
done
echo
echo -n "# Final valid prob "
for x in $*; do
prob=$(grep Overall $x/log/compute_prob_valid.final.log | grep -v xent | awk '{printf("%.4f", $8)}')
printf "% 10s" $prob
done
echo
echo -n "# Final train prob (xent) "
for x in $*; do
prob=$(grep Overall $x/log/compute_prob_train.final.log | grep -w xent | awk '{printf("%.4f", $8)}')
printf "% 10s" $prob
done
echo
echo -n "# Final valid prob (xent) "
for x in $*; do
prob=$(grep Overall $x/log/compute_prob_valid.final.log | grep -w xent | awk '{printf("%.4f", $8)}')
printf "% 10s" $prob
done
echo