run.sh
5.51 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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
#!/bin/bash
# Copyright 2019 Beijing DataTang Tech. Co. Ltd. (Author: Liyuan Wang)
# 2017 Hui Bu
# 2017 Jiayu Du
# 2017 Xingyu Na
# 2017 Bengu Wu
# 2017 Hao Zheng
# Apache 2.0
# This is a shell script, but it's recommended that you run the commands one by
# one by copying and pasting into the shell.
# Caution: some of the graph creation steps use quite a bit of memory, so you
# should run this on a machine that has sufficient memory.
. ./cmd.sh ## You'll want to change cmd.sh to something that will work on your system.
## This relates to the queue.
. ./path.sh
# corpus directory and download URL
data=/export/a05/xna/data
data_url=www.openslr.org/resources/62
# Obtain the database
#[ -d $data ] || mkdir -p $data || exit 1;
local/download_and_untar.sh $data $data_url aidatatang_200zh || exit 1;
# Data Preparation: generate text, wav.scp, utt2spk, spk2utt
local/data_prep.sh $data/aidatatang_200zh/corpus $data/aidatatang_200zh/transcript || exit 1;
# Lexicon Preparation: build a large lexicon that invovles words in both the training and decoding
local/prepare_dict.sh || exit 1;
# Prepare Language Stuff
# Phone Sets, questions, L compilation
utils/prepare_lang.sh --position-dependent-phones false data/local/dict "<UNK>" data/local/lang data/lang || exit 1;
# LM training
local/train_lms.sh || exit 1;
# G compilation, check LG composition
local/format_data.sh
# Now make MFCC plus pitch features.
# mfccdir should be some place with a largish disk where you want to store MFCC features.
mfccdir=mfcc
for x in train dev test; do
steps/make_mfcc_pitch.sh --write_utt2dur false --write_utt2num_frames false --cmd "$train_cmd" --nj 10 data/$x exp/make_mfcc/$x $mfccdir || exit 1;
steps/compute_cmvn_stats.sh data/$x exp/make_mfcc/$x $mfccdir || exit 1;
utils/fix_data_dir.sh data/$x || exit 1;
done
steps/train_mono.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/mono || exit 1;
# Monophone decoding
utils/mkgraph.sh data/lang_test exp/mono exp/mono/graph || exit 1;
steps/decode.sh --cmd "$decode_cmd" --config conf/decode.config --nj 10 \
exp/mono/graph data/dev exp/mono/decode_dev
steps/decode.sh --cmd "$decode_cmd" --config conf/decode.config --nj 10 \
exp/mono/graph data/test exp/mono/decode_test
# Get alignments from monophone system.
steps/align_si.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/mono exp/mono_ali || exit 1;
# train tri1 [first triphone pass]
steps/train_deltas.sh --cmd "$train_cmd" \
2500 20000 data/train data/lang exp/mono_ali exp/tri1 || exit 1;
# decode tri1
utils/mkgraph.sh data/lang_test exp/tri1 exp/tri1/graph || exit 1;
steps/decode.sh --cmd "$decode_cmd" --config conf/decode.config --nj 10 \
exp/tri1/graph data/dev exp/tri1/decode_dev
steps/decode.sh --cmd "$decode_cmd" --config conf/decode.config --nj 10 \
exp/tri1/graph data/test exp/tri1/decode_test
# align tri1
steps/align_si.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/tri1 exp/tri1_ali || exit 1;
# train tri2 [delta+delta-deltas]
steps/train_deltas.sh --cmd "$train_cmd" \
2500 20000 data/train data/lang exp/tri1_ali exp/tri2 || exit 1;
# decode tri2
utils/mkgraph.sh data/lang_test exp/tri2 exp/tri2/graph
steps/decode.sh --cmd "$decode_cmd" --config conf/decode.config --nj 10 \
exp/tri2/graph data/dev exp/tri2/decode_dev
steps/decode.sh --cmd "$decode_cmd" --config conf/decode.config --nj 10 \
exp/tri2/graph data/test exp/tri2/decode_test
#align tri2
steps/align_si.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/tri2 exp/tri2_ali || exit 1;
# Train tri3a, which is LDA+MLLT,
steps/train_lda_mllt.sh --cmd "$train_cmd" \
2500 20000 data/train data/lang exp/tri2_ali exp/tri3a || exit 1;
utils/mkgraph.sh data/lang_test exp/tri3a exp/tri3a/graph || exit 1;
steps/decode.sh --cmd "$decode_cmd" --nj 10 --config conf/decode.config \
exp/tri3a/graph data/dev exp/tri3a/decode_dev
steps/decode.sh --cmd "$decode_cmd" --nj 10 --config conf/decode.config \
exp/tri3a/graph data/test exp/tri3a/decode_test
# From now, we start building a more serious system (with SAT), and we'll
# do the alignment with fMLLR.
steps/align_fmllr.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/tri3a exp/tri3a_ali || exit 1;
steps/train_sat.sh --cmd "$train_cmd" \
2500 20000 data/train data/lang exp/tri3a_ali exp/tri4a || exit 1;
utils/mkgraph.sh data/lang_test exp/tri4a exp/tri4a/graph
steps/decode_fmllr.sh --cmd "$decode_cmd" --nj 10 --config conf/decode.config \
exp/tri4a/graph data/dev exp/tri4a/decode_dev
steps/decode_fmllr.sh --cmd "$decode_cmd" --nj 10 --config conf/decode.config \
exp/tri4a/graph data/test exp/tri4a/decode_test
steps/align_fmllr.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/tri4a exp/tri4a_ali
# Building a larger SAT system.
steps/train_sat.sh --cmd "$train_cmd" \
3500 100000 data/train data/lang exp/tri4a_ali exp/tri5a || exit 1;
utils/mkgraph.sh data/lang_test exp/tri5a exp/tri5a/graph || exit 1;
steps/decode_fmllr.sh --cmd "$decode_cmd" --nj 10 --config conf/decode.config \
exp/tri5a/graph data/dev exp/tri5a/decode_dev || exit 1;
steps/decode_fmllr.sh --cmd "$decode_cmd" --nj 10 --config conf/decode.config \
exp/tri5a/graph data/test exp/tri5a/decode_test || exit 1;
steps/align_fmllr.sh --cmd "$train_cmd" --nj 10 \
data/train data/lang exp/tri5a exp/tri5a_ali || exit 1;
# nnet3
local/nnet3/run_tdnn.sh
# chain
local/chain/run_tdnn.sh
# getting results (see RESULTS file)
for x in exp/*/decode_test; do [ -d $x ] && grep WER $x/cer_* | utils/best_wer.sh; done 2>/dev/null
exit 0;