Blame view

egs/aspire/s5/local/fisher_create_test_lang.sh 1.62 KB
8dcb6dfcb   Yannick Estève   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
  #!/bin/bash
  #
  
  if [ -f path.sh ]; then . ./path.sh; fi
  
  mkdir -p data/lang_test
  
  arpa_lm=data/local/lm/3gram-mincount/lm_unpruned.gz
  [ ! -f $arpa_lm ] && echo No such file $arpa_lm && exit 1;
  
  cp -rT data/lang data/lang_test
  
  gunzip -c "$arpa_lm" | \
     arpa2fst --disambig-symbol=#0 \
              --read-symbol-table=data/lang_test/words.txt - data/lang_test/G.fst
  
  echo  "Checking how stochastic G is (the first of these numbers should be small):"
  fstisstochastic data/lang_test/G.fst
  
  ## Check lexicon.
  ## just have a look and make sure it seems sane.
  echo "First few lines of lexicon FST:"
  fstprint   --isymbols=data/lang/phones.txt --osymbols=data/lang/words.txt data/lang/L.fst  | head
  
  echo Performing further checks
  
  # Checking that G.fst is determinizable.
  fstdeterminize data/lang_test/G.fst /dev/null || echo Error determinizing G.
  
  # Checking that L_disambig.fst is determinizable.
  fstdeterminize data/lang_test/L_disambig.fst /dev/null || echo Error determinizing L.
  
  # Checking that disambiguated lexicon times G is determinizable
  # Note: we do this with fstdeterminizestar not fstdeterminize, as
  # fstdeterminize was taking forever (presumbaly relates to a bug
  # in this version of OpenFst that makes determinization slow for
  # some case).
  fsttablecompose data/lang_test/L_disambig.fst data/lang_test/G.fst | \
     fstdeterminizestar >/dev/null || echo Error
  
  # Checking that LG is stochastic:
  fsttablecompose data/lang/L_disambig.fst data/lang_test/G.fst | \
     fstisstochastic || echo "[log:] LG is not stochastic"
  
  
  utils/build_const_arpa_lm.sh \
      data/local/lm/4gram-mincount/lm_unpruned.gz data/lang data/lang_test_fg
  
  echo "$0 succeeded"