run_nnet2_baseline.sh
2.44 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
#!/bin/bash
. ./cmd.sh
stage=1
train_stage=-10
use_gpu=true
. ./cmd.sh
. ./path.sh
. ./utils/parse_options.sh
if $use_gpu; then
if ! cuda-compiled; then
cat <<EOF && exit 1
This script is intended to be used with GPUs but you have not compiled Kaldi with CUDA
If you want to use GPUs (and have them), go to src/, and configure and make on a machine
where "nvcc" is installed. Otherwise, call this script with --use-gpu false
EOF
fi
parallel_opts="--gpu 1"
num_threads=1
minibatch_size=512
# the _a is in case I want to change the parameters.
dir=exp/nnet2_online/nnet_a_gpu_baseline
else
# Use 4 nnet jobs just like run_4d_gpu.sh so the results should be
# almost the same, but this may be a little bit slow.
num_threads=16
minibatch_size=128
parallel_opts="--num-threads $num_threads"
dir=exp/nnet2_online/nnet_a_baseline
fi
if [ $stage -le 1 ]; then
# train without iVectors.
steps/nnet2/train_pnorm_fast.sh --stage $train_stage \
--num-epochs 8 --num-epochs-extra 4 \
--splice-width 7 --feat-type raw \
--cmvn-opts "--norm-means=false --norm-vars=false" \
--num-threads "$num_threads" \
--minibatch-size "$minibatch_size" \
--parallel-opts "$parallel_opts" \
--num-jobs-nnet 6 \
--num-hidden-layers 4 \
--mix-up 4000 \
--initial-learning-rate 0.02 --final-learning-rate 0.004 \
--cmd "$decode_cmd" \
--pnorm-input-dim 2400 \
--pnorm-output-dim 300 \
data/train_si284 data/lang exp/tri4b_ali_si284 $dir || exit 1;
fi
if [ $stage -le 2 ]; then
for lm_suffix in tgpr bd_tgpr; do
graph_dir=exp/tri4b/graph_${lm_suffix}
# use already-built graphs.
for year in eval92 dev93; do
steps/nnet2/decode.sh --nj 8 --cmd "$decode_cmd" \
$graph_dir data/test_$year $dir/decode_${lm_suffix}_${year} || exit 1;
done
done
fi
if [ $stage -le 3 ]; then
# If this setup used PLP features, we'd have to give the option --feature-type plp
# to the script below.
steps/online/nnet2/prepare_online_decoding.sh data/lang "$dir" ${dir}_online || exit 1;
fi
if [ $stage -le 4 ]; then
# Decode. The --per-utt true option makes no difference to the results here.
for lm_suffix in tgpr bd_tgpr; do
graph_dir=exp/tri4b/graph_${lm_suffix}
for year in eval92 dev93; do
steps/online/nnet2/decode.sh --cmd "$decode_cmd" --nj 8 \
--per-utt true \
"$graph_dir" data/test_${year} ${dir}_online/decode_${lm_suffix}_${year}_utt || exit 1;
done
done
fi