Blame view
egs/rm/s5/local/run_pitch.sh
8.82 KB
8dcb6dfcb
first commit
|
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
#!/bin/bash
# This is like ../run.sh but with pitch; it's included to demonstrate the
# online-decoding with pitch.
. ./cmd.sh
set -e # exit on error
# call the next line with the directory where the RM data is
# (the argument below is just an example). This should contain
# subdirectories named as follows:
# rm1_audio1 rm1_audio2 rm2_audio
#local/rm_data_prep.sh /mnt/matylda2/data/RM
local/rm_data_prep.sh /export/corpora5/LDC/LDC93S3A/rm_comp
#local/rm_data_prep.sh /home/dpovey/data/LDC93S3A/rm_comp
utils/prepare_lang.sh data/local/dict '!SIL' data/local/lang data/lang
local/rm_prepare_grammar.sh # Traditional RM grammar (bigram word-pair)
local/rm_prepare_grammar_ug.sh # Unigram grammar (gives worse results, but
# changes in WER will be more significant.)
# mfccdir should be some place with a largish disk where you
# want to store MFCC features. You can make a soft link if you want.
featdir=mfcc
for x in test_mar87 test_oct87 test_feb89 test_oct89 test_feb91 test_sep92 train; do
steps/make_mfcc_pitch.sh --nj 8 --cmd "run.pl" data/$x exp/make_feat/$x $featdir
# steps/make_plp_pitch.sh --nj 8 --cmd "run.pl" data/$x exp/make_feat/$x $featdir
steps/compute_cmvn_stats.sh --fake-dims 13:14:15 data/$x exp/make_feat/$x $featdir
done
# Make a combined data dir where the data from all the test sets goes-- we do
# all our testing on this averaged set. This is just less hassle. We
# regenerate the CMVN stats as one of the speakers appears in two of the
# test sets; otherwise tools complain as the archive has 2 entries.
utils/combine_data.sh data/test data/test_{mar87,oct87,feb89,oct89,feb91,sep92}
steps/compute_cmvn_stats.sh data/test exp/make_feat/test $featdir
utils/subset_data_dir.sh data/train 1000 data/train.1k
steps/train_mono.sh --nj 4 --cmd "$train_cmd" data/train.1k data/lang exp/mono
#show-transitions data/lang/phones.txt exp/tri2a/final.mdl exp/tri2a/final.occs | perl -e 'while(<>) { if (m/ sil /) { $l = <>; $l =~ m/pdf = (\d+)/|| die "bad line $l"; $tot += $1; }} print "Total silence count $tot
";'
utils/mkgraph.sh data/lang exp/mono exp/mono/graph
steps/decode.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
exp/mono/graph data/test exp/mono/decode
# Get alignments from monophone system.
steps/align_si.sh --nj 8 --cmd "$train_cmd" \
data/train data/lang exp/mono exp/mono_ali
# train tri1 [first triphone pass]
steps/train_deltas.sh --cmd "$train_cmd" \
1800 9000 data/train data/lang exp/mono_ali exp/tri1
# decode tri1
utils/mkgraph.sh data/lang exp/tri1 exp/tri1/graph
steps/decode.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
exp/tri1/graph data/test exp/tri1/decode
local/test_decoders.sh # This is a test program that we run only in the
# RM setup, it does some comparison tests on decoders
# to help validate the code.
#draw-tree data/lang/phones.txt exp/tri1/tree | dot -Tps -Gsize=8,10.5 | ps2pdf - tree.pdf
# align tri1
steps/align_si.sh --nj 8 --cmd "$train_cmd" \
--use-graphs true data/train data/lang exp/tri1 exp/tri1_ali
# train tri2a [delta+delta-deltas]
steps/train_deltas.sh --cmd "$train_cmd" 1800 9000 \
data/train data/lang exp/tri1_ali exp/tri2a
# decode tri2a
utils/mkgraph.sh data/lang exp/tri2a exp/tri2a/graph
steps/decode.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
exp/tri2a/graph data/test exp/tri2a/decode
# train and decode tri2b [LDA+MLLT]
steps/train_lda_mllt.sh --cmd "$train_cmd" \
--splice-opts "--left-context=3 --right-context=3" \
1800 9000 data/train data/lang exp/tri1_ali exp/tri2b
utils/mkgraph.sh data/lang exp/tri2b exp/tri2b/graph
steps/decode.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b/decode
# Align all data with LDA+MLLT system (tri2b)
steps/align_si.sh --nj 8 --cmd "$train_cmd" --use-graphs true \
data/train data/lang exp/tri2b exp/tri2b_ali
# Do MMI on top of LDA+MLLT.
steps/make_denlats.sh --nj 8 --cmd "$train_cmd" \
data/train data/lang exp/tri2b exp/tri2b_denlats
steps/train_mmi.sh data/train data/lang exp/tri2b_ali exp/tri2b_denlats exp/tri2b_mmi
steps/decode.sh --config conf/decode.config --iter 4 --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b_mmi/decode_it4
steps/decode.sh --config conf/decode.config --iter 3 --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b_mmi/decode_it3
# Do the same with boosting.
steps/train_mmi.sh --boost 0.05 data/train data/lang \
exp/tri2b_ali exp/tri2b_denlats exp/tri2b_mmi_b0.05
steps/decode.sh --config conf/decode.config --iter 4 --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b_mmi_b0.05/decode_it4
steps/decode.sh --config conf/decode.config --iter 3 --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b_mmi_b0.05/decode_it3
# Do MPE.
steps/train_mpe.sh data/train data/lang exp/tri2b_ali exp/tri2b_denlats exp/tri2b_mpe
steps/decode.sh --config conf/decode.config --iter 4 --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b_mpe/decode_it4
steps/decode.sh --config conf/decode.config --iter 3 --nj 20 --cmd "$decode_cmd" \
exp/tri2b/graph data/test exp/tri2b_mpe/decode_it3
## Do LDA+MLLT+SAT, and decode.
steps/train_sat.sh 1800 9000 data/train data/lang exp/tri2b_ali exp/tri3b
utils/mkgraph.sh data/lang exp/tri3b exp/tri3b/graph
steps/decode_fmllr.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
exp/tri3b/graph data/test exp/tri3b/decode
(
utils/mkgraph.sh data/lang_ug exp/tri3b exp/tri3b/graph_ug
steps/decode_fmllr.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
exp/tri3b/graph_ug data/test exp/tri3b/decode_ug
)
# Align all data with LDA+MLLT+SAT system (tri3b)
steps/align_fmllr.sh --nj 8 --cmd "$train_cmd" --use-graphs true \
data/train data/lang exp/tri3b exp/tri3b_ali
## MMI on top of tri3b (i.e. LDA+MLLT+SAT+MMI)
steps/make_denlats.sh --config conf/decode.config \
--nj 8 --cmd "$train_cmd" --transform-dir exp/tri3b_ali \
data/train data/lang exp/tri3b exp/tri3b_denlats
steps/train_mmi.sh data/train data/lang exp/tri3b_ali exp/tri3b_denlats exp/tri3b_mmi
steps/decode_fmllr.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
--alignment-model exp/tri3b/final.alimdl --adapt-model exp/tri3b/final.mdl \
exp/tri3b/graph data/test exp/tri3b_mmi/decode
# Do a decoding that uses the exp/tri3b/decode directory to get transforms from.
steps/decode.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
--transform-dir exp/tri3b/decode exp/tri3b/graph data/test exp/tri3b_mmi/decode2
## MMI on top of tri3b (i.e. LDA+MLLT+SAT+MMI)
steps/make_denlats.sh --config conf/decode.config \
--nj 8 --cmd "$train_cmd" --transform-dir exp/tri3b_ali \
data/train data/lang exp/tri3b exp/tri3b_denlats
steps/train_mmi.sh data/train data/lang exp/tri3b_ali exp/tri3b_denlats exp/tri3b_mmi
steps/decode_fmllr.sh --config conf/decode.config --nj 20 --cmd "$decode_cmd" \
--alignment-model exp/tri3b/final.alimdl --adapt-model exp/tri3b/final.mdl \
exp/tri3b/graph data/test exp/tri3b_mmi/decode
# demonstration script for online decoding.
#local/online/run_gmm_pitch.sh
#first, train UBM for fMMI experiments.
steps/train_diag_ubm.sh --silence-weight 0.5 --nj 8 --cmd "$train_cmd" \
250 data/train data/lang exp/tri3b_ali exp/dubm3b
# Next, various fMMI+MMI configurations.
steps/train_mmi_fmmi.sh --learning-rate 0.0025 \
--boost 0.1 --cmd "$train_cmd" data/train data/lang exp/tri3b_ali exp/dubm3b exp/tri3b_denlats \
exp/tri3b_fmmi_b
for iter in 3 4 5 6 7 8; do
steps/decode_fmmi.sh --nj 20 --config conf/decode.config --cmd "$decode_cmd" --iter $iter \
--transform-dir exp/tri3b/decode exp/tri3b/graph data/test exp/tri3b_fmmi_b/decode_it$iter &
done
steps/train_mmi_fmmi.sh --learning-rate 0.001 \
--boost 0.1 --cmd "$train_cmd" data/train data/lang exp/tri3b_ali exp/dubm3b exp/tri3b_denlats \
exp/tri3b_fmmi_c
for iter in 3 4 5 6 7 8; do
steps/decode_fmmi.sh --nj 20 --config conf/decode.config --cmd "$decode_cmd" --iter $iter \
--transform-dir exp/tri3b/decode exp/tri3b/graph data/test exp/tri3b_fmmi_c/decode_it$iter &
done
# for indirect one, use twice the learning rate.
steps/train_mmi_fmmi_indirect.sh --learning-rate 0.01 --schedule "fmmi fmmi fmmi fmmi mmi mmi mmi mmi" \
--boost 0.1 --cmd "$train_cmd" data/train data/lang exp/tri3b_ali exp/dubm3b exp/tri3b_denlats \
exp/tri3b_fmmi_d
for iter in 3 4 5 6 7 8; do
steps/decode_fmmi.sh --nj 20 --config conf/decode.config --cmd "$decode_cmd" --iter $iter \
--transform-dir exp/tri3b/decode exp/tri3b/graph data/test exp/tri3b_fmmi_d/decode_it$iter &
done
# Demo of "raw fMLLR"
# local/run_raw_fmllr.sh
# You don't have to run all 3 of the below, e.g. you can just run the run_sgmm2.sh
local/run_sgmm2.sh
#local/run_sgmm2x.sh
# The following script depends on local/run_raw_fmllr.sh having been run.
#
# local/run_nnet2.sh
|