running path.sh
running cmd.sh

===== VALIDATING DATA =====


utils/validate_data_dir.sh: file data/train/utt2spk is not sorted or has duplicates
utils/validate_data_dir.sh: file data/test/utt2spk is not sorted or has duplicates
utils/fix_data_dir.sh: file data/train/utt2spk is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/train/spk2utt is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/train/text is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/train/segments is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/train/wav.scp is not in sorted order or not unique, sorting it
fix_data_dir.sh: kept all 10647 utterances.
fix_data_dir.sh: old files are kept in data/train/.backup
utils/fix_data_dir.sh: file data/test/utt2spk is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/test/spk2utt is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/test/text is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/test/segments is not in sorted order or not unique, sorting it
utils/fix_data_dir.sh: file data/test/wav.scp is not in sorted order or not unique, sorting it
fix_data_dir.sh: kept all 2101 utterances.
fix_data_dir.sh: old files are kept in data/test/.backup
utils/prepare_lang.sh data/local/dict_nosp <UNK> data/local/lang_tmp_nosp data/lang_nosp
Checking data/local/dict_nosp/silence_phones.txt ...
--> reading data/local/dict_nosp/silence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/silence_phones.txt is OK

Checking data/local/dict_nosp/optional_silence.txt ...
--> reading data/local/dict_nosp/optional_silence.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/optional_silence.txt is OK

Checking data/local/dict_nosp/nonsilence_phones.txt ...
--> reading data/local/dict_nosp/nonsilence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/nonsilence_phones.txt is OK

Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.

Checking data/local/dict_nosp/lexicon.txt
--> reading data/local/dict_nosp/lexicon.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/lexicon.txt is OK

Checking data/local/dict_nosp/extra_questions.txt ...
--> data/local/dict_nosp/extra_questions.txt is empty (this is OK)
--> SUCCESS [validating dictionary directory data/local/dict_nosp]

**Creating data/local/dict_nosp/lexiconp.txt from data/local/dict_nosp/lexicon.txt
prepare_lang.sh: validating output directory
utils/validate_lang.pl data/lang_nosp
Checking existence of separator file
separator file data/lang_nosp/subword_separator.txt is empty or does not exist, deal in word case.
Checking data/lang_nosp/phones.txt ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_nosp/phones.txt is OK

Checking words.txt: #0 ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_nosp/words.txt is OK

Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
--> silence.txt and nonsilence.txt are disjoint
--> silence.txt and disambig.txt are disjoint
--> disambig.txt and nonsilence.txt are disjoint
--> disjoint property is OK

Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
--> found no unexplainable phones in phones.txt

Checking data/lang_nosp/phones/context_indep.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_nosp/phones/context_indep.txt
--> data/lang_nosp/phones/context_indep.int corresponds to data/lang_nosp/phones/context_indep.txt
--> data/lang_nosp/phones/context_indep.csl corresponds to data/lang_nosp/phones/context_indep.txt
--> data/lang_nosp/phones/context_indep.{txt, int, csl} are OK

Checking data/lang_nosp/phones/nonsilence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 160 entry/entries in data/lang_nosp/phones/nonsilence.txt
--> data/lang_nosp/phones/nonsilence.int corresponds to data/lang_nosp/phones/nonsilence.txt
--> data/lang_nosp/phones/nonsilence.csl corresponds to data/lang_nosp/phones/nonsilence.txt
--> data/lang_nosp/phones/nonsilence.{txt, int, csl} are OK

Checking data/lang_nosp/phones/silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_nosp/phones/silence.txt
--> data/lang_nosp/phones/silence.int corresponds to data/lang_nosp/phones/silence.txt
--> data/lang_nosp/phones/silence.csl corresponds to data/lang_nosp/phones/silence.txt
--> data/lang_nosp/phones/silence.{txt, int, csl} are OK

Checking data/lang_nosp/phones/optional_silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.int corresponds to data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.csl corresponds to data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.{txt, int, csl} are OK

Checking data/lang_nosp/phones/disambig.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 6 entry/entries in data/lang_nosp/phones/disambig.txt
--> data/lang_nosp/phones/disambig.int corresponds to data/lang_nosp/phones/disambig.txt
--> data/lang_nosp/phones/disambig.csl corresponds to data/lang_nosp/phones/disambig.txt
--> data/lang_nosp/phones/disambig.{txt, int, csl} are OK

Checking data/lang_nosp/phones/roots.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_nosp/phones/roots.txt
--> data/lang_nosp/phones/roots.int corresponds to data/lang_nosp/phones/roots.txt
--> data/lang_nosp/phones/roots.{txt, int} are OK

Checking data/lang_nosp/phones/sets.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_nosp/phones/sets.txt
--> data/lang_nosp/phones/sets.int corresponds to data/lang_nosp/phones/sets.txt
--> data/lang_nosp/phones/sets.{txt, int} are OK

Checking data/lang_nosp/phones/extra_questions.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 9 entry/entries in data/lang_nosp/phones/extra_questions.txt
--> data/lang_nosp/phones/extra_questions.int corresponds to data/lang_nosp/phones/extra_questions.txt
--> data/lang_nosp/phones/extra_questions.{txt, int} are OK

Checking data/lang_nosp/phones/word_boundary.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 175 entry/entries in data/lang_nosp/phones/word_boundary.txt
--> data/lang_nosp/phones/word_boundary.int corresponds to data/lang_nosp/phones/word_boundary.txt
--> data/lang_nosp/phones/word_boundary.{txt, int} are OK

Checking optional_silence.txt ...
--> reading data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.txt is OK

Checking disambiguation symbols: #0 and #1
--> data/lang_nosp/phones/disambig.txt has "#0" and "#1"
--> data/lang_nosp/phones/disambig.txt is OK

Checking topo ...

Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
--> data/lang_nosp/phones/word_boundary.txt doesn't include disambiguation symbols
--> data/lang_nosp/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
--> data/lang_nosp/phones/word_boundary.txt is OK

Checking word-level disambiguation symbols...
--> data/lang_nosp/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking word_boundary.int and disambig.int
--> generating a 5 word/subword sequence
--> resulting phone sequence from L.fst corresponds to the word sequence
--> L.fst is OK
--> generating a 92 word/subword sequence
--> resulting phone sequence from L_disambig.fst corresponds to the word sequence
--> L_disambig.fst is OK

Checking data/lang_nosp/oov.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_nosp/oov.txt
--> data/lang_nosp/oov.int corresponds to data/lang_nosp/oov.txt
--> data/lang_nosp/oov.{txt, int} are OK

--> data/lang_nosp/L.fst is olabel sorted
--> data/lang_nosp/L_disambig.fst is olabel sorted
--> SUCCESS [validating lang directory data/lang_nosp]
utils/validate_lang.pl data/lang_nosp
Checking existence of separator file
separator file data/lang_nosp/subword_separator.txt is empty or does not exist, deal in word case.
Checking data/lang_nosp/phones.txt ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_nosp/phones.txt is OK

Checking words.txt: #0 ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_nosp/words.txt is OK

Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
--> silence.txt and nonsilence.txt are disjoint
--> silence.txt and disambig.txt are disjoint
--> disambig.txt and nonsilence.txt are disjoint
--> disjoint property is OK

Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
--> found no unexplainable phones in phones.txt

Checking data/lang_nosp/phones/context_indep.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_nosp/phones/context_indep.txt
--> data/lang_nosp/phones/context_indep.int corresponds to data/lang_nosp/phones/context_indep.txt
--> data/lang_nosp/phones/context_indep.csl corresponds to data/lang_nosp/phones/context_indep.txt
--> data/lang_nosp/phones/context_indep.{txt, int, csl} are OK

Checking data/lang_nosp/phones/nonsilence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 160 entry/entries in data/lang_nosp/phones/nonsilence.txt
--> data/lang_nosp/phones/nonsilence.int corresponds to data/lang_nosp/phones/nonsilence.txt
--> data/lang_nosp/phones/nonsilence.csl corresponds to data/lang_nosp/phones/nonsilence.txt
--> data/lang_nosp/phones/nonsilence.{txt, int, csl} are OK

Checking data/lang_nosp/phones/silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_nosp/phones/silence.txt
--> data/lang_nosp/phones/silence.int corresponds to data/lang_nosp/phones/silence.txt
--> data/lang_nosp/phones/silence.csl corresponds to data/lang_nosp/phones/silence.txt
--> data/lang_nosp/phones/silence.{txt, int, csl} are OK

Checking data/lang_nosp/phones/optional_silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.int corresponds to data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.csl corresponds to data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.{txt, int, csl} are OK

Checking data/lang_nosp/phones/disambig.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 6 entry/entries in data/lang_nosp/phones/disambig.txt
--> data/lang_nosp/phones/disambig.int corresponds to data/lang_nosp/phones/disambig.txt
--> data/lang_nosp/phones/disambig.csl corresponds to data/lang_nosp/phones/disambig.txt
--> data/lang_nosp/phones/disambig.{txt, int, csl} are OK

Checking data/lang_nosp/phones/roots.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_nosp/phones/roots.txt
--> data/lang_nosp/phones/roots.int corresponds to data/lang_nosp/phones/roots.txt
--> data/lang_nosp/phones/roots.{txt, int} are OK

Checking data/lang_nosp/phones/sets.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_nosp/phones/sets.txt
--> data/lang_nosp/phones/sets.int corresponds to data/lang_nosp/phones/sets.txt
--> data/lang_nosp/phones/sets.{txt, int} are OK

Checking data/lang_nosp/phones/extra_questions.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 9 entry/entries in data/lang_nosp/phones/extra_questions.txt
--> data/lang_nosp/phones/extra_questions.int corresponds to data/lang_nosp/phones/extra_questions.txt
--> data/lang_nosp/phones/extra_questions.{txt, int} are OK

Checking data/lang_nosp/phones/word_boundary.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 175 entry/entries in data/lang_nosp/phones/word_boundary.txt
--> data/lang_nosp/phones/word_boundary.int corresponds to data/lang_nosp/phones/word_boundary.txt
--> data/lang_nosp/phones/word_boundary.{txt, int} are OK

Checking optional_silence.txt ...
--> reading data/lang_nosp/phones/optional_silence.txt
--> data/lang_nosp/phones/optional_silence.txt is OK

Checking disambiguation symbols: #0 and #1
--> data/lang_nosp/phones/disambig.txt has "#0" and "#1"
--> data/lang_nosp/phones/disambig.txt is OK

Checking topo ...

Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
--> data/lang_nosp/phones/word_boundary.txt doesn't include disambiguation symbols
--> data/lang_nosp/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
--> data/lang_nosp/phones/word_boundary.txt is OK

Checking word-level disambiguation symbols...
--> data/lang_nosp/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking word_boundary.int and disambig.int
--> generating a 28 word/subword sequence
--> resulting phone sequence from L.fst corresponds to the word sequence
--> L.fst is OK
--> generating a 99 word/subword sequence
--> resulting phone sequence from L_disambig.fst corresponds to the word sequence
--> L_disambig.fst is OK

Checking data/lang_nosp/oov.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_nosp/oov.txt
--> data/lang_nosp/oov.int corresponds to data/lang_nosp/oov.txt
--> data/lang_nosp/oov.{txt, int} are OK

--> data/lang_nosp/L.fst is olabel sorted
--> data/lang_nosp/L_disambig.fst is olabel sorted
--> SUCCESS [validating lang directory data/lang_nosp]
Checking data/local/dict_nosp/silence_phones.txt ...
--> reading data/local/dict_nosp/silence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/silence_phones.txt is OK

Checking data/local/dict_nosp/optional_silence.txt ...
--> reading data/local/dict_nosp/optional_silence.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/optional_silence.txt is OK

Checking data/local/dict_nosp/nonsilence_phones.txt ...
--> reading data/local/dict_nosp/nonsilence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/nonsilence_phones.txt is OK

Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.

Checking data/local/dict_nosp/lexicon.txt
--> reading data/local/dict_nosp/lexicon.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/lexicon.txt is OK

Checking data/local/dict_nosp/lexiconp.txt
--> reading data/local/dict_nosp/lexiconp.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/lexiconp.txt is OK

Checking lexicon pair data/local/dict_nosp/lexicon.txt and data/local/dict_nosp/lexiconp.txt
--> lexicon pair data/local/dict_nosp/lexicon.txt and data/local/dict_nosp/lexiconp.txt match

Checking data/local/dict_nosp/extra_questions.txt ...
--> data/local/dict_nosp/extra_questions.txt is empty (this is OK)
--> SUCCESS [validating dictionary directory data/local/dict_nosp]

done

===== FEATURES EXTRACTION =====

steps/make_mfcc.sh --nj 3 --cmd run.pl --mem 2G data/train exp/make_mfcc/train mfcc
utils/validate_data_dir.sh: Successfully validated data-directory data/train
steps/make_mfcc.sh [info]: segments file exists: using that.
steps/make_mfcc.sh: Succeeded creating MFCC features for train
steps/make_mfcc.sh --nj 3 --cmd run.pl --mem 2G data/test exp/make_mfcc/test mfcc
utils/validate_data_dir.sh: Successfully validated data-directory data/test
steps/make_mfcc.sh [info]: segments file exists: using that.
steps/make_mfcc.sh: Succeeded creating MFCC features for test
steps/compute_cmvn_stats.sh data/train exp/make_mfcc/train mfcc
Succeeded creating CMVN stats for train
steps/compute_cmvn_stats.sh data/test exp/make_mfcc/test mfcc
Succeeded creating CMVN stats for test

===== LANGUAGE MODEL CREATION =====
==== MAKING lm.arpa ====

done

==== MAKING G.fst ====

data/local/tmp/lm.arpa

===== MONO TRAINING =====

steps/train_mono.sh --boost-silence 1.25 --nj 3 --cmd run.pl --mem 2G data/train data/lang_nosp exp/mono
steps/train_mono.sh: Initializing monophone system.
steps/train_mono.sh: Compiling training graphs
steps/train_mono.sh: Aligning data equally (pass 0)
steps/train_mono.sh: Pass 1
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 2
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 3
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 4
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 5
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 6
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 7
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 8
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 9
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 10
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 11
steps/train_mono.sh: Pass 12
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 13
steps/train_mono.sh: Pass 14
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 15
steps/train_mono.sh: Pass 16
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 17
steps/train_mono.sh: Pass 18
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 19
steps/train_mono.sh: Pass 20
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 21
steps/train_mono.sh: Pass 22
steps/train_mono.sh: Pass 23
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 24
steps/train_mono.sh: Pass 25
steps/train_mono.sh: Pass 26
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 27
steps/train_mono.sh: Pass 28
steps/train_mono.sh: Pass 29
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 30
steps/train_mono.sh: Pass 31
steps/train_mono.sh: Pass 32
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 33
steps/train_mono.sh: Pass 34
steps/train_mono.sh: Pass 35
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 36
steps/train_mono.sh: Pass 37
steps/train_mono.sh: Pass 38
steps/train_mono.sh: Aligning data
steps/train_mono.sh: Pass 39
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/mono
steps/diagnostic/analyze_alignments.sh: see stats in exp/mono/log/analyze_alignments.log
3315 warnings in exp/mono/log/acc.*.*.log
13526 warnings in exp/mono/log/align.*.*.log
200 warnings in exp/mono/log/update.*.log
exp/mono: nj=3 align prob=-100.19 over 13.20h [retry=2.7%, fail=0.6%] states=135 gauss=976
steps/train_mono.sh: Done training monophone system in exp/mono

===== MONO DECODING =====

WARNING: the --mono, --left-biphone and --quinphone options are now deprecated and ignored.
-0.0747975 -0.0754266
[info]: LG not stochastic.
-0.0747975 -0.0754266
[info]: CLG not stochastic.
0.000348064 -0.14873
HCLGa is not stochastic

===== MONO ALIGNMENT =====

steps/align_si.sh --boost-silence 1.25 --nj 3 --cmd run.pl --mem 2G data/train data/lang_nosp exp/mono exp/mono_ali_train
steps/align_si.sh: feature type is delta
steps/align_si.sh: aligning data in data/train using model from exp/mono, putting alignments in exp/mono_ali_train
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/mono_ali_train
steps/diagnostic/analyze_alignments.sh: see stats in exp/mono_ali_train/log/analyze_alignments.log
steps/align_si.sh: done aligning data.

===== TRI1 (first triphone pass) TRAINING =====

steps/train_deltas.sh --boost-silence 1.25 --cmd run.pl --mem 2G 2000 10000 data/train data/lang_nosp exp/mono_ali_train exp/tri1
steps/train_deltas.sh: accumulating tree stats
steps/train_deltas.sh: getting questions for tree-building, via clustering
steps/train_deltas.sh: building the tree
WARNING (gmm-init-model[5.5.1060~1-ae8cb]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 1 with no stats; corresponding phone list: 6 7 8 9 10 
** The warnings above about 'no stats' generally mean you have phones **
** (or groups of phones) in your phone set that had no corresponding data. **
** You should probably figure out whether something went wrong, **
** or whether your data just doesn't happen to have examples of those **
** phones. **
steps/train_deltas.sh: converting alignments from exp/mono_ali_train to use current tree
steps/train_deltas.sh: compiling graphs of transcripts
steps/train_deltas.sh: training pass 1
steps/train_deltas.sh: training pass 2
steps/train_deltas.sh: training pass 3
steps/train_deltas.sh: training pass 4
steps/train_deltas.sh: training pass 5
steps/train_deltas.sh: training pass 6
steps/train_deltas.sh: training pass 7
steps/train_deltas.sh: training pass 8
steps/train_deltas.sh: training pass 9
steps/train_deltas.sh: training pass 10
steps/train_deltas.sh: aligning data
steps/train_deltas.sh: training pass 11
steps/train_deltas.sh: training pass 12
steps/train_deltas.sh: training pass 13
steps/train_deltas.sh: training pass 14
steps/train_deltas.sh: training pass 15
steps/train_deltas.sh: training pass 16
steps/train_deltas.sh: training pass 17
steps/train_deltas.sh: training pass 18
steps/train_deltas.sh: training pass 19
steps/train_deltas.sh: training pass 20
steps/train_deltas.sh: aligning data
steps/train_deltas.sh: training pass 21
steps/train_deltas.sh: training pass 22
steps/train_deltas.sh: training pass 23
steps/train_deltas.sh: training pass 24
steps/train_deltas.sh: training pass 25
steps/train_deltas.sh: training pass 26
steps/train_deltas.sh: training pass 27
steps/train_deltas.sh: training pass 28
steps/train_deltas.sh: training pass 29
steps/train_deltas.sh: training pass 30
steps/train_deltas.sh: aligning data
steps/train_deltas.sh: training pass 31
steps/train_deltas.sh: training pass 32
steps/train_deltas.sh: training pass 33
steps/train_deltas.sh: training pass 34
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/tri1
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri1/log/analyze_alignments.log
2723 warnings in exp/tri1/log/acc.*.*.log
1 warnings in exp/tri1/log/build_tree.log
34 warnings in exp/tri1/log/update.*.log
1 warnings in exp/tri1/log/questions.log
1187 warnings in exp/tri1/log/align.*.*.log
2 warnings in exp/tri1/log/init_model.log
exp/tri1: nj=3 align prob=-98.18 over 13.17h [retry=2.7%, fail=0.8%] states=1592 gauss=10025 tree-impr=3.52
steps/train_deltas.sh: Done training system with delta+delta-delta features in exp/tri1

===== TRI1 (first triphone pass) DECODING =====

0 -0.0754266
[info]: CLG not stochastic.
0.5776 -0.204193
HCLGa is not stochastic

===== TRI1 ALIGNMENT =====

steps/align_si.sh --nj 3 --cmd run.pl --mem 2G data/train data/lang_nosp exp/tri1 exp/tri1_ali_train
steps/align_si.sh: feature type is delta
steps/align_si.sh: aligning data in data/train using model from exp/tri1, putting alignments in exp/tri1_ali_train
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/tri1_ali_train
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri1_ali_train/log/analyze_alignments.log
steps/align_si.sh: done aligning data.

===== train an LDA+MLLT system =====

steps/train_lda_mllt.sh --cmd run.pl --mem 2G --splice-opts --left-context=3 --right-context=3 2500 15000 data/train data/lang_nosp exp/tri1_ali_train exp/tri2b
steps/train_lda_mllt.sh: Accumulating LDA statistics.
steps/train_lda_mllt.sh: Accumulating tree stats
steps/train_lda_mllt.sh: Getting questions for tree clustering.
steps/train_lda_mllt.sh: Building the tree
steps/train_lda_mllt.sh: Initializing the model
WARNING (gmm-init-model[5.5.1060~1-ae8cb]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 1 with no stats; corresponding phone list: 6 7 8 9 10 
This is a bad warning.
steps/train_lda_mllt.sh: Converting alignments from exp/tri1_ali_train to use current tree
steps/train_lda_mllt.sh: Compiling graphs of transcripts
Training pass 1
Training pass 2
steps/train_lda_mllt.sh: Estimating MLLT
Training pass 3
Training pass 4
steps/train_lda_mllt.sh: Estimating MLLT
Training pass 5
Training pass 6
steps/train_lda_mllt.sh: Estimating MLLT
Training pass 7
Training pass 8
Training pass 9
Training pass 10
Aligning data
Training pass 11
Training pass 12
steps/train_lda_mllt.sh: Estimating MLLT
Training pass 13
Training pass 14
Training pass 15
Training pass 16
Training pass 17
Training pass 18
Training pass 19
Training pass 20
Aligning data
Training pass 21
Training pass 22
Training pass 23
Training pass 24
Training pass 25
Training pass 26
Training pass 27
Training pass 28
Training pass 29
Training pass 30
Aligning data
Training pass 31
Training pass 32
Training pass 33
Training pass 34
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/tri2b
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri2b/log/analyze_alignments.log
34 warnings in exp/tri2b/log/update.*.log
3231 warnings in exp/tri2b/log/acc.*.*.log
1194 warnings in exp/tri2b/log/align.*.*.log
1 warnings in exp/tri2b/log/build_tree.log
79 warnings in exp/tri2b/log/lda_acc.*.log
9 warnings in exp/tri2b/log/init_model.log
1 warnings in exp/tri2b/log/questions.log
exp/tri2b: nj=3 align prob=-48.54 over 13.16h [retry=2.4%, fail=0.9%] states=1944 gauss=15027 tree-impr=3.89 lda-sum=15.80 mllt:impr,logdet=0.98,1.47
steps/train_lda_mllt.sh: Done training system with LDA+MLLT features in exp/tri2b

===== Align utts using the tri2b model =====

steps/align_si.sh --nj 3 --cmd run.pl --mem 2G --use-graphs true data/train data/lang_nosp exp/tri2b exp/tri2b_ali_train
steps/align_si.sh: feature type is lda
steps/align_si.sh: aligning data in data/train using model from exp/tri2b, putting alignments in exp/tri2b_ali_train
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/tri2b_ali_train
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri2b_ali_train/log/analyze_alignments.log
steps/align_si.sh: done aligning data.

===== Train tri3b, which is LDA+MLLT+SAT =====

steps/train_sat.sh --cmd run.pl --mem 2G 2500 15000 data/train data/lang_nosp exp/tri2b_ali_train exp/tri3b
steps/train_sat.sh: feature type is lda
steps/train_sat.sh: obtaining initial fMLLR transforms since not present in exp/tri2b_ali_train
steps/train_sat.sh: Accumulating tree stats
steps/train_sat.sh: Getting questions for tree clustering.
steps/train_sat.sh: Building the tree
steps/train_sat.sh: Initializing the model
WARNING (gmm-init-model[5.5.1060~1-ae8cb]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 1 with no stats; corresponding phone list: 6 7 8 9 10 
This is a bad warning.
steps/train_sat.sh: Converting alignments from exp/tri2b_ali_train to use current tree
steps/train_sat.sh: Compiling graphs of transcripts
Pass 1
Pass 2
Estimating fMLLR transforms
Pass 3
Pass 4
Estimating fMLLR transforms
Pass 5
Pass 6
Estimating fMLLR transforms
Pass 7
Pass 8
Pass 9
Pass 10
Aligning data
Pass 11
Pass 12
Estimating fMLLR transforms
Pass 13
Pass 14
Pass 15
Pass 16
Pass 17
Pass 18
Pass 19
Pass 20
Aligning data
Pass 21
Pass 22
Pass 23
Pass 24
Pass 25
Pass 26
Pass 27
Pass 28
Pass 29
Pass 30
Aligning data
Pass 31
Pass 32
Pass 33
Pass 34
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang_nosp exp/tri3b
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3b/log/analyze_alignments.log
1 warnings in exp/tri3b/log/build_tree.log
1 warnings in exp/tri3b/log/questions.log
446 warnings in exp/tri3b/log/fmllr.*.*.log
3 warnings in exp/tri3b/log/est_alimdl.log
507 warnings in exp/tri3b/log/align.*.*.log
5 warnings in exp/tri3b/log/init_model.log
56 warnings in exp/tri3b/log/update.*.log
1156 warnings in exp/tri3b/log/acc.*.*.log
steps/train_sat.sh: Likelihood evolution:
-51.0209 -50.7623 -50.5801 -50.2915 -49.4398 -48.8264 -48.5046 -48.266 -48.0496 -47.4596 -47.2318 -47.0404 -46.8976 -46.7857 -46.6792 -46.5809 -46.4908 -46.4151 -46.3406 -46.1813 -46.0752 -46.0089 -45.9487 -45.8954 -45.8486 -45.8039 -45.7591 -45.7148 -45.6732 -45.5879 -45.5246 -45.4979 -45.4815 -45.4701 
exp/tri3b: nj=3 align prob=-48.38 over 13.27h [retry=1.1%, fail=0.1%] states=2040 gauss=15018 fmllr-impr=2.51 over 9.92h tree-impr=5.85
steps/train_sat.sh: done training SAT system in exp/tri3b

===== compute the pronunciation and silence probabilities =====

steps/get_prons.sh --cmd run.pl --mem 2G data/train data/lang_nosp exp/tri3b
steps/get_prons.sh: exp/tri3b/ali.1.gz exists, so starting from alignments.
steps/get_prons.sh: done writing prons to exp/tri3b/prons.*.gz, silence counts in 
steps/get_prons.sh: exp/tri3b/sil_counts_nowb.txt and pronunciation counts in 
steps/get_prons.sh: exp/tri3b/pron_counts.{int,txt}
steps/get_prons.sh: ... and also in exp/tri3b/pron_counts_nowb.txt
Checking data/local/dict_nosp/silence_phones.txt ...
--> reading data/local/dict_nosp/silence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/silence_phones.txt is OK

Checking data/local/dict_nosp/optional_silence.txt ...
--> reading data/local/dict_nosp/optional_silence.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/optional_silence.txt is OK

Checking data/local/dict_nosp/nonsilence_phones.txt ...
--> reading data/local/dict_nosp/nonsilence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/nonsilence_phones.txt is OK

Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.

Checking data/local/dict_nosp/lexicon.txt
--> reading data/local/dict_nosp/lexicon.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/lexicon.txt is OK

Checking data/local/dict_nosp/lexiconp.txt
--> reading data/local/dict_nosp/lexiconp.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict_nosp/lexiconp.txt is OK

Checking lexicon pair data/local/dict_nosp/lexicon.txt and data/local/dict_nosp/lexiconp.txt
--> lexicon pair data/local/dict_nosp/lexicon.txt and data/local/dict_nosp/lexiconp.txt match

Checking data/local/dict_nosp/extra_questions.txt ...
--> data/local/dict_nosp/extra_questions.txt is empty (this is OK)
--> SUCCESS [validating dictionary directory data/local/dict_nosp]

utils/dict_dir_add_pronprobs.sh: normalizing pronprobs so maximum is 1 for each word.
utils/dict_dir_add_pronprobs.sh: produced dictionary directory with probabilities in data/local/dict/
utils/dict_dir_add_pronprobs.sh: validating data/local/dict ..
Checking data/local/dict/silence_phones.txt ...
--> reading data/local/dict/silence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ...
--> reading data/local/dict/optional_silence.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ...
--> reading data/local/dict/nonsilence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/nonsilence_phones.txt is OK

Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.

Checking data/local/dict/lexicon.txt
--> reading data/local/dict/lexicon.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexicon.txt is OK

Checking data/local/dict/lexiconp.txt
--> reading data/local/dict/lexiconp.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexiconp.txt is OK

Checking data/local/dict/lexiconp_silprob.txt
--> reading data/local/dict/lexiconp_silprob.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexiconp_silprob.txt is OK

Checking lexicon pair data/local/dict/lexicon.txt and data/local/dict/lexiconp.txt
--> lexicon pair data/local/dict/lexicon.txt and data/local/dict/lexiconp.txt match

Checking lexicon pair data/local/dict/lexiconp.txt and data/local/dict/lexiconp_silprob.txt
--> lexicon pair data/local/dict/lexiconp.txt and data/local/dict/lexiconp_silprob.txt match

Checking data/local/dict/extra_questions.txt ...
--> data/local/dict/extra_questions.txt is empty (this is OK)
--> SUCCESS [validating dictionary directory data/local/dict]

Some low-probability prons include: 
# sort -k2,2 -n data/local/dict/lexiconp.txt  | head -n 8
anezho 0.019802 N EH
neuze 0.0277777 N EN N
petra 0.0434782 P E R
evit 0.045994 E W I T
petra 0.0521739 P E R A
marteze 0.054054 M A R S EH
ivez 0.0569395 I V E Z
anezho 0.059406 N EU
utils/prepare_lang.sh data/local/dict <UNK> data/local/lang_tmp data/lang
Checking data/local/dict/silence_phones.txt ...
--> reading data/local/dict/silence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ...
--> reading data/local/dict/optional_silence.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ...
--> reading data/local/dict/nonsilence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/nonsilence_phones.txt is OK

Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.

Checking data/local/dict/lexicon.txt
--> reading data/local/dict/lexicon.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexicon.txt is OK

Checking data/local/dict/lexiconp.txt
--> reading data/local/dict/lexiconp.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexiconp.txt is OK

Checking data/local/dict/lexiconp_silprob.txt
--> reading data/local/dict/lexiconp_silprob.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexiconp_silprob.txt is OK

Checking lexicon pair data/local/dict/lexicon.txt and data/local/dict/lexiconp.txt
--> lexicon pair data/local/dict/lexicon.txt and data/local/dict/lexiconp.txt match

Checking lexicon pair data/local/dict/lexiconp.txt and data/local/dict/lexiconp_silprob.txt
--> lexicon pair data/local/dict/lexiconp.txt and data/local/dict/lexiconp_silprob.txt match

Checking data/local/dict/extra_questions.txt ...
--> data/local/dict/extra_questions.txt is empty (this is OK)
--> SUCCESS [validating dictionary directory data/local/dict]

prepare_lang.sh: validating output directory
utils/validate_lang.pl data/lang
Checking existence of separator file
separator file data/lang/subword_separator.txt is empty or does not exist, deal in word case.
Checking data/lang/phones.txt ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang/phones.txt is OK

Checking words.txt: #0 ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang/words.txt is OK

Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
--> silence.txt and nonsilence.txt are disjoint
--> silence.txt and disambig.txt are disjoint
--> disambig.txt and nonsilence.txt are disjoint
--> disjoint property is OK

Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
--> found no unexplainable phones in phones.txt

Checking data/lang/phones/context_indep.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang/phones/context_indep.txt
--> data/lang/phones/context_indep.int corresponds to data/lang/phones/context_indep.txt
--> data/lang/phones/context_indep.csl corresponds to data/lang/phones/context_indep.txt
--> data/lang/phones/context_indep.{txt, int, csl} are OK

Checking data/lang/phones/nonsilence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 160 entry/entries in data/lang/phones/nonsilence.txt
--> data/lang/phones/nonsilence.int corresponds to data/lang/phones/nonsilence.txt
--> data/lang/phones/nonsilence.csl corresponds to data/lang/phones/nonsilence.txt
--> data/lang/phones/nonsilence.{txt, int, csl} are OK

Checking data/lang/phones/silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang/phones/silence.txt
--> data/lang/phones/silence.int corresponds to data/lang/phones/silence.txt
--> data/lang/phones/silence.csl corresponds to data/lang/phones/silence.txt
--> data/lang/phones/silence.{txt, int, csl} are OK

Checking data/lang/phones/optional_silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.int corresponds to data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.csl corresponds to data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.{txt, int, csl} are OK

Checking data/lang/phones/disambig.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 6 entry/entries in data/lang/phones/disambig.txt
--> data/lang/phones/disambig.int corresponds to data/lang/phones/disambig.txt
--> data/lang/phones/disambig.csl corresponds to data/lang/phones/disambig.txt
--> data/lang/phones/disambig.{txt, int, csl} are OK

Checking data/lang/phones/roots.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang/phones/roots.txt
--> data/lang/phones/roots.int corresponds to data/lang/phones/roots.txt
--> data/lang/phones/roots.{txt, int} are OK

Checking data/lang/phones/sets.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang/phones/sets.txt
--> data/lang/phones/sets.int corresponds to data/lang/phones/sets.txt
--> data/lang/phones/sets.{txt, int} are OK

Checking data/lang/phones/extra_questions.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 9 entry/entries in data/lang/phones/extra_questions.txt
--> data/lang/phones/extra_questions.int corresponds to data/lang/phones/extra_questions.txt
--> data/lang/phones/extra_questions.{txt, int} are OK

Checking data/lang/phones/word_boundary.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 175 entry/entries in data/lang/phones/word_boundary.txt
--> data/lang/phones/word_boundary.int corresponds to data/lang/phones/word_boundary.txt
--> data/lang/phones/word_boundary.{txt, int} are OK

Checking optional_silence.txt ...
--> reading data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.txt is OK

Checking disambiguation symbols: #0 and #1
--> data/lang/phones/disambig.txt has "#0" and "#1"
--> data/lang/phones/disambig.txt is OK

Checking topo ...

Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
--> data/lang/phones/word_boundary.txt doesn't include disambiguation symbols
--> data/lang/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
--> data/lang/phones/word_boundary.txt is OK

Checking word-level disambiguation symbols...
--> data/lang/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking word_boundary.int and disambig.int
--> generating a 78 word/subword sequence
--> resulting phone sequence from L.fst corresponds to the word sequence
--> L.fst is OK
--> generating a 20 word/subword sequence
--> resulting phone sequence from L_disambig.fst corresponds to the word sequence
--> L_disambig.fst is OK

Checking data/lang/oov.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang/oov.txt
--> data/lang/oov.int corresponds to data/lang/oov.txt
--> data/lang/oov.{txt, int} are OK

--> data/lang/L.fst is olabel sorted
--> data/lang/L_disambig.fst is olabel sorted
--> SUCCESS [validating lang directory data/lang]
utils/validate_lang.pl data/lang
Checking existence of separator file
separator file data/lang/subword_separator.txt is empty or does not exist, deal in word case.
Checking data/lang/phones.txt ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang/phones.txt is OK

Checking words.txt: #0 ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang/words.txt is OK

Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
--> silence.txt and nonsilence.txt are disjoint
--> silence.txt and disambig.txt are disjoint
--> disambig.txt and nonsilence.txt are disjoint
--> disjoint property is OK

Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
--> found no unexplainable phones in phones.txt

Checking data/lang/phones/context_indep.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang/phones/context_indep.txt
--> data/lang/phones/context_indep.int corresponds to data/lang/phones/context_indep.txt
--> data/lang/phones/context_indep.csl corresponds to data/lang/phones/context_indep.txt
--> data/lang/phones/context_indep.{txt, int, csl} are OK

Checking data/lang/phones/nonsilence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 160 entry/entries in data/lang/phones/nonsilence.txt
--> data/lang/phones/nonsilence.int corresponds to data/lang/phones/nonsilence.txt
--> data/lang/phones/nonsilence.csl corresponds to data/lang/phones/nonsilence.txt
--> data/lang/phones/nonsilence.{txt, int, csl} are OK

Checking data/lang/phones/silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang/phones/silence.txt
--> data/lang/phones/silence.int corresponds to data/lang/phones/silence.txt
--> data/lang/phones/silence.csl corresponds to data/lang/phones/silence.txt
--> data/lang/phones/silence.{txt, int, csl} are OK

Checking data/lang/phones/optional_silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.int corresponds to data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.csl corresponds to data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.{txt, int, csl} are OK

Checking data/lang/phones/disambig.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 6 entry/entries in data/lang/phones/disambig.txt
--> data/lang/phones/disambig.int corresponds to data/lang/phones/disambig.txt
--> data/lang/phones/disambig.csl corresponds to data/lang/phones/disambig.txt
--> data/lang/phones/disambig.{txt, int, csl} are OK

Checking data/lang/phones/roots.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang/phones/roots.txt
--> data/lang/phones/roots.int corresponds to data/lang/phones/roots.txt
--> data/lang/phones/roots.{txt, int} are OK

Checking data/lang/phones/sets.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang/phones/sets.txt
--> data/lang/phones/sets.int corresponds to data/lang/phones/sets.txt
--> data/lang/phones/sets.{txt, int} are OK

Checking data/lang/phones/extra_questions.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 9 entry/entries in data/lang/phones/extra_questions.txt
--> data/lang/phones/extra_questions.int corresponds to data/lang/phones/extra_questions.txt
--> data/lang/phones/extra_questions.{txt, int} are OK

Checking data/lang/phones/word_boundary.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 175 entry/entries in data/lang/phones/word_boundary.txt
--> data/lang/phones/word_boundary.int corresponds to data/lang/phones/word_boundary.txt
--> data/lang/phones/word_boundary.{txt, int} are OK

Checking optional_silence.txt ...
--> reading data/lang/phones/optional_silence.txt
--> data/lang/phones/optional_silence.txt is OK

Checking disambiguation symbols: #0 and #1
--> data/lang/phones/disambig.txt has "#0" and "#1"
--> data/lang/phones/disambig.txt is OK

Checking topo ...

Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
--> data/lang/phones/word_boundary.txt doesn't include disambiguation symbols
--> data/lang/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
--> data/lang/phones/word_boundary.txt is OK

Checking word-level disambiguation symbols...
--> data/lang/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking word_boundary.int and disambig.int
--> generating a 35 word/subword sequence
--> resulting phone sequence from L.fst corresponds to the word sequence
--> L.fst is OK
--> generating a 52 word/subword sequence
--> resulting phone sequence from L_disambig.fst corresponds to the word sequence
--> L_disambig.fst is OK

Checking data/lang/oov.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang/oov.txt
--> data/lang/oov.int corresponds to data/lang/oov.txt
--> data/lang/oov.{txt, int} are OK

--> data/lang/L.fst is olabel sorted
--> data/lang/L_disambig.fst is olabel sorted
--> SUCCESS [validating lang directory data/lang]
Checking data/local/dict/silence_phones.txt ...
--> reading data/local/dict/silence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ...
--> reading data/local/dict/optional_silence.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ...
--> reading data/local/dict/nonsilence_phones.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/nonsilence_phones.txt is OK

Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.

Checking data/local/dict/lexicon.txt
--> reading data/local/dict/lexicon.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexicon.txt is OK

Checking data/local/dict/lexiconp.txt
--> reading data/local/dict/lexiconp.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexiconp.txt is OK

Checking data/local/dict/lexiconp_silprob.txt
--> reading data/local/dict/lexiconp_silprob.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/lexiconp_silprob.txt is OK

Checking lexicon pair data/local/dict/lexicon.txt and data/local/dict/lexiconp.txt
--> lexicon pair data/local/dict/lexicon.txt and data/local/dict/lexiconp.txt match

Checking lexicon pair data/local/dict/lexiconp.txt and data/local/dict/lexiconp_silprob.txt
--> lexicon pair data/local/dict/lexiconp.txt and data/local/dict/lexiconp_silprob.txt match

Checking data/local/dict/extra_questions.txt ...
--> data/local/dict/extra_questions.txt is empty (this is OK)
--> SUCCESS [validating dictionary directory data/local/dict]

******* format_lms **********
utils/validate_lang.pl data/lang_test_tgsmall
Checking existence of separator file
separator file data/lang_test_tgsmall/subword_separator.txt is empty or does not exist, deal in word case.
Checking data/lang_test_tgsmall/phones.txt ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_test_tgsmall/phones.txt is OK

Checking words.txt: #0 ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_test_tgsmall/words.txt is OK

Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
--> silence.txt and nonsilence.txt are disjoint
--> silence.txt and disambig.txt are disjoint
--> disambig.txt and nonsilence.txt are disjoint
--> disjoint property is OK

Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
--> found no unexplainable phones in phones.txt

Checking data/lang_test_tgsmall/phones/context_indep.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_test_tgsmall/phones/context_indep.txt
--> data/lang_test_tgsmall/phones/context_indep.int corresponds to data/lang_test_tgsmall/phones/context_indep.txt
--> data/lang_test_tgsmall/phones/context_indep.csl corresponds to data/lang_test_tgsmall/phones/context_indep.txt
--> data/lang_test_tgsmall/phones/context_indep.{txt, int, csl} are OK

Checking data/lang_test_tgsmall/phones/nonsilence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 160 entry/entries in data/lang_test_tgsmall/phones/nonsilence.txt
--> data/lang_test_tgsmall/phones/nonsilence.int corresponds to data/lang_test_tgsmall/phones/nonsilence.txt
--> data/lang_test_tgsmall/phones/nonsilence.csl corresponds to data/lang_test_tgsmall/phones/nonsilence.txt
--> data/lang_test_tgsmall/phones/nonsilence.{txt, int, csl} are OK

Checking data/lang_test_tgsmall/phones/silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_test_tgsmall/phones/silence.txt
--> data/lang_test_tgsmall/phones/silence.int corresponds to data/lang_test_tgsmall/phones/silence.txt
--> data/lang_test_tgsmall/phones/silence.csl corresponds to data/lang_test_tgsmall/phones/silence.txt
--> data/lang_test_tgsmall/phones/silence.{txt, int, csl} are OK

Checking data/lang_test_tgsmall/phones/optional_silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_test_tgsmall/phones/optional_silence.txt
--> data/lang_test_tgsmall/phones/optional_silence.int corresponds to data/lang_test_tgsmall/phones/optional_silence.txt
--> data/lang_test_tgsmall/phones/optional_silence.csl corresponds to data/lang_test_tgsmall/phones/optional_silence.txt
--> data/lang_test_tgsmall/phones/optional_silence.{txt, int, csl} are OK

Checking data/lang_test_tgsmall/phones/disambig.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 6 entry/entries in data/lang_test_tgsmall/phones/disambig.txt
--> data/lang_test_tgsmall/phones/disambig.int corresponds to data/lang_test_tgsmall/phones/disambig.txt
--> data/lang_test_tgsmall/phones/disambig.csl corresponds to data/lang_test_tgsmall/phones/disambig.txt
--> data/lang_test_tgsmall/phones/disambig.{txt, int, csl} are OK

Checking data/lang_test_tgsmall/phones/roots.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_test_tgsmall/phones/roots.txt
--> data/lang_test_tgsmall/phones/roots.int corresponds to data/lang_test_tgsmall/phones/roots.txt
--> data/lang_test_tgsmall/phones/roots.{txt, int} are OK

Checking data/lang_test_tgsmall/phones/sets.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_test_tgsmall/phones/sets.txt
--> data/lang_test_tgsmall/phones/sets.int corresponds to data/lang_test_tgsmall/phones/sets.txt
--> data/lang_test_tgsmall/phones/sets.{txt, int} are OK

Checking data/lang_test_tgsmall/phones/extra_questions.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 9 entry/entries in data/lang_test_tgsmall/phones/extra_questions.txt
--> data/lang_test_tgsmall/phones/extra_questions.int corresponds to data/lang_test_tgsmall/phones/extra_questions.txt
--> data/lang_test_tgsmall/phones/extra_questions.{txt, int} are OK

Checking data/lang_test_tgsmall/phones/word_boundary.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 175 entry/entries in data/lang_test_tgsmall/phones/word_boundary.txt
--> data/lang_test_tgsmall/phones/word_boundary.int corresponds to data/lang_test_tgsmall/phones/word_boundary.txt
--> data/lang_test_tgsmall/phones/word_boundary.{txt, int} are OK

Checking optional_silence.txt ...
--> reading data/lang_test_tgsmall/phones/optional_silence.txt
--> data/lang_test_tgsmall/phones/optional_silence.txt is OK

Checking disambiguation symbols: #0 and #1
--> data/lang_test_tgsmall/phones/disambig.txt has "#0" and "#1"
--> data/lang_test_tgsmall/phones/disambig.txt is OK

Checking topo ...

Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
--> data/lang_test_tgsmall/phones/word_boundary.txt doesn't include disambiguation symbols
--> data/lang_test_tgsmall/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
--> data/lang_test_tgsmall/phones/word_boundary.txt is OK

Checking word-level disambiguation symbols...
--> data/lang_test_tgsmall/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking word_boundary.int and disambig.int
--> generating a 66 word/subword sequence
--> resulting phone sequence from L.fst corresponds to the word sequence
--> L.fst is OK
--> generating a 87 word/subword sequence
--> resulting phone sequence from L_disambig.fst corresponds to the word sequence
--> L_disambig.fst is OK

Checking data/lang_test_tgsmall/oov.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_test_tgsmall/oov.txt
--> data/lang_test_tgsmall/oov.int corresponds to data/lang_test_tgsmall/oov.txt
--> data/lang_test_tgsmall/oov.{txt, int} are OK

--> data/lang_test_tgsmall/L.fst is olabel sorted
--> data/lang_test_tgsmall/L_disambig.fst is olabel sorted
--> data/lang_test_tgsmall/G.fst is ilabel sorted
--> data/lang_test_tgsmall/G.fst has 131820 states
--> utils/lang/check_g_properties.pl successfully validated data/lang_test_tgsmall/G.fst
--> utils/lang/check_g_properties.pl succeeded.
--> SUCCESS [validating lang directory data/lang_test_tgsmall]
utils/validate_lang.pl data/lang_test_tgmed
Checking existence of separator file
separator file data/lang_test_tgmed/subword_separator.txt is empty or does not exist, deal in word case.
Checking data/lang_test_tgmed/phones.txt ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_test_tgmed/phones.txt is OK

Checking words.txt: #0 ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/lang_test_tgmed/words.txt is OK

Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
--> silence.txt and nonsilence.txt are disjoint
--> silence.txt and disambig.txt are disjoint
--> disambig.txt and nonsilence.txt are disjoint
--> disjoint property is OK

Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
--> found no unexplainable phones in phones.txt

Checking data/lang_test_tgmed/phones/context_indep.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_test_tgmed/phones/context_indep.txt
--> data/lang_test_tgmed/phones/context_indep.int corresponds to data/lang_test_tgmed/phones/context_indep.txt
--> data/lang_test_tgmed/phones/context_indep.csl corresponds to data/lang_test_tgmed/phones/context_indep.txt
--> data/lang_test_tgmed/phones/context_indep.{txt, int, csl} are OK

Checking data/lang_test_tgmed/phones/nonsilence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 160 entry/entries in data/lang_test_tgmed/phones/nonsilence.txt
--> data/lang_test_tgmed/phones/nonsilence.int corresponds to data/lang_test_tgmed/phones/nonsilence.txt
--> data/lang_test_tgmed/phones/nonsilence.csl corresponds to data/lang_test_tgmed/phones/nonsilence.txt
--> data/lang_test_tgmed/phones/nonsilence.{txt, int, csl} are OK

Checking data/lang_test_tgmed/phones/silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 15 entry/entries in data/lang_test_tgmed/phones/silence.txt
--> data/lang_test_tgmed/phones/silence.int corresponds to data/lang_test_tgmed/phones/silence.txt
--> data/lang_test_tgmed/phones/silence.csl corresponds to data/lang_test_tgmed/phones/silence.txt
--> data/lang_test_tgmed/phones/silence.{txt, int, csl} are OK

Checking data/lang_test_tgmed/phones/optional_silence.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_test_tgmed/phones/optional_silence.txt
--> data/lang_test_tgmed/phones/optional_silence.int corresponds to data/lang_test_tgmed/phones/optional_silence.txt
--> data/lang_test_tgmed/phones/optional_silence.csl corresponds to data/lang_test_tgmed/phones/optional_silence.txt
--> data/lang_test_tgmed/phones/optional_silence.{txt, int, csl} are OK

Checking data/lang_test_tgmed/phones/disambig.{txt, int, csl} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 6 entry/entries in data/lang_test_tgmed/phones/disambig.txt
--> data/lang_test_tgmed/phones/disambig.int corresponds to data/lang_test_tgmed/phones/disambig.txt
--> data/lang_test_tgmed/phones/disambig.csl corresponds to data/lang_test_tgmed/phones/disambig.txt
--> data/lang_test_tgmed/phones/disambig.{txt, int, csl} are OK

Checking data/lang_test_tgmed/phones/roots.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_test_tgmed/phones/roots.txt
--> data/lang_test_tgmed/phones/roots.int corresponds to data/lang_test_tgmed/phones/roots.txt
--> data/lang_test_tgmed/phones/roots.{txt, int} are OK

Checking data/lang_test_tgmed/phones/sets.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 43 entry/entries in data/lang_test_tgmed/phones/sets.txt
--> data/lang_test_tgmed/phones/sets.int corresponds to data/lang_test_tgmed/phones/sets.txt
--> data/lang_test_tgmed/phones/sets.{txt, int} are OK

Checking data/lang_test_tgmed/phones/extra_questions.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 9 entry/entries in data/lang_test_tgmed/phones/extra_questions.txt
--> data/lang_test_tgmed/phones/extra_questions.int corresponds to data/lang_test_tgmed/phones/extra_questions.txt
--> data/lang_test_tgmed/phones/extra_questions.{txt, int} are OK

Checking data/lang_test_tgmed/phones/word_boundary.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 175 entry/entries in data/lang_test_tgmed/phones/word_boundary.txt
--> data/lang_test_tgmed/phones/word_boundary.int corresponds to data/lang_test_tgmed/phones/word_boundary.txt
--> data/lang_test_tgmed/phones/word_boundary.{txt, int} are OK

Checking optional_silence.txt ...
--> reading data/lang_test_tgmed/phones/optional_silence.txt
--> data/lang_test_tgmed/phones/optional_silence.txt is OK

Checking disambiguation symbols: #0 and #1
--> data/lang_test_tgmed/phones/disambig.txt has "#0" and "#1"
--> data/lang_test_tgmed/phones/disambig.txt is OK

Checking topo ...

Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
--> data/lang_test_tgmed/phones/word_boundary.txt doesn't include disambiguation symbols
--> data/lang_test_tgmed/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
--> data/lang_test_tgmed/phones/word_boundary.txt is OK

Checking word-level disambiguation symbols...
--> data/lang_test_tgmed/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking word_boundary.int and disambig.int
--> generating a 20 word/subword sequence
--> resulting phone sequence from L.fst corresponds to the word sequence
--> L.fst is OK
--> generating a 10 word/subword sequence
--> resulting phone sequence from L_disambig.fst corresponds to the word sequence
--> L_disambig.fst is OK

Checking data/lang_test_tgmed/oov.{txt, int} ...
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> 1 entry/entries in data/lang_test_tgmed/oov.txt
--> data/lang_test_tgmed/oov.int corresponds to data/lang_test_tgmed/oov.txt
--> data/lang_test_tgmed/oov.{txt, int} are OK

--> data/lang_test_tgmed/L.fst is olabel sorted
--> data/lang_test_tgmed/L_disambig.fst is olabel sorted
--> data/lang_test_tgmed/G.fst is ilabel sorted
--> data/lang_test_tgmed/G.fst has 131820 states
--> utils/lang/check_g_properties.pl successfully validated data/lang_test_tgmed/G.fst
--> utils/lang/check_g_properties.pl succeeded.
--> SUCCESS [validating lang directory data/lang_test_tgmed]
******* build_const_arpa *****
****** align_fmllr ********
steps/align_fmllr.sh --nj 3 --cmd run.pl --mem 2G data/train data/lang exp/tri3b exp/tri3b_ali_train
steps/align_fmllr.sh: feature type is lda
steps/align_fmllr.sh: compiling training graphs
steps/align_fmllr.sh: aligning data in data/train using exp/tri3b/final.alimdl and speaker-independent features.
steps/align_fmllr.sh: computing fMLLR transforms
steps/align_fmllr.sh: doing final alignment.
steps/align_fmllr.sh: done aligning data.
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang exp/tri3b_ali_train
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3b_ali_train/log/analyze_alignments.log
15 warnings in exp/tri3b_ali_train/log/fmllr.*.log
127 warnings in exp/tri3b_ali_train/log/align_pass1.*.log
119 warnings in exp/tri3b_ali_train/log/align_pass2.*.log

===== STAGE 9 =====
==== Test the tri3b system with the silprobs and pron-probs ====

-0.0633072 -0.0641278
[info]: LG not stochastic.
0 -0.0641278
[info]: CLG not stochastic.
0.649718 -0.194716
HCLGa is not stochastic
****** decode_fmllr.sh ******
steps/decode_fmllr.sh --nj 3 --cmd run.pl --mem 4G exp/tri3b/graph_tgsmall data/test exp/tri3b/decode_tgsmall_test
steps/decode.sh --scoring-opts  --num-threads 1 --skip-scoring false --acwt 0.083333 --nj 3 --cmd run.pl --mem 4G --beam 10.0 --model exp/tri3b/final.alimdl --max-active 2000 exp/tri3b/graph_tgsmall data/test exp/tri3b/decode_tgsmall_test.si
decode.sh: feature type is lda
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 4G exp/tri3b/graph_tgsmall exp/tri3b/decode_tgsmall_test.si
steps/diagnostic/analyze_lats.sh: see stats in exp/tri3b/decode_tgsmall_test.si/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,9,41) and mean=16.7
steps/diagnostic/analyze_lats.sh: see stats in exp/tri3b/decode_tgsmall_test.si/log/analyze_lattice_depth_stats.log
exp/tri3b/decode_tgsmall_test.si/wer_10
%WER 61.62 [ 6615 / 10735, 1069 ins, 872 del, 4674 sub ]
%SER 86.58 [ 1819 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_11
%WER 60.43 [ 6487 / 10735, 969 ins, 943 del, 4575 sub ]
%SER 86.20 [ 1811 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_12
%WER 59.40 [ 6377 / 10735, 856 ins, 999 del, 4522 sub ]
%SER 85.63 [ 1799 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_13
%WER 59.04 [ 6338 / 10735, 775 ins, 1081 del, 4482 sub ]
%SER 85.15 [ 1789 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_14
%WER 58.30 [ 6258 / 10735, 715 ins, 1104 del, 4439 sub ]
%SER 84.91 [ 1784 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_15
%WER 58.19 [ 6247 / 10735, 653 ins, 1174 del, 4420 sub ]
%SER 84.72 [ 1780 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_16
%WER 58.21 [ 6249 / 10735, 618 ins, 1228 del, 4403 sub ]
%SER 84.77 [ 1781 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_17
%WER 58.32 [ 6261 / 10735, 601 ins, 1280 del, 4380 sub ]
%SER 84.77 [ 1781 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_7
%WER 67.38 [ 7233 / 10735, 1569 ins, 655 del, 5009 sub ]
%SER 89.39 [ 1878 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_8
%WER 64.96 [ 6973 / 10735, 1382 ins, 719 del, 4872 sub ]
%SER 88.58 [ 1861 / 2101 ]
exp/tri3b/decode_tgsmall_test.si/wer_9
%WER 63.17 [ 6781 / 10735, 1216 ins, 787 del, 4778 sub ]
%SER 87.48 [ 1838 / 2101 ]
steps/decode_fmllr.sh: feature type is lda
steps/decode_fmllr.sh: getting first-pass fMLLR transforms.
steps/decode_fmllr.sh: doing main lattice generation phase
steps/decode_fmllr.sh: estimating fMLLR transforms a second time.
steps/decode_fmllr.sh: doing a final pass of acoustic rescoring.
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 4G exp/tri3b/graph_tgsmall exp/tri3b/decode_tgsmall_test
steps/diagnostic/analyze_lats.sh: see stats in exp/tri3b/decode_tgsmall_test/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,6,35) and mean=13.6
steps/diagnostic/analyze_lats.sh: see stats in exp/tri3b/decode_tgsmall_test/log/analyze_lattice_depth_stats.log
exp/tri3b/decode_tgsmall_test/wer_10
%WER 50.19 [ 5388 / 10735, 922 ins, 697 del, 3769 sub ]
%SER 80.58 [ 1693 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_11
%WER 49.19 [ 5281 / 10735, 849 ins, 717 del, 3715 sub ]
%SER 80.15 [ 1684 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_12
%WER 48.51 [ 5208 / 10735, 782 ins, 744 del, 3682 sub ]
%SER 79.68 [ 1674 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_13
%WER 47.81 [ 5132 / 10735, 714 ins, 776 del, 3642 sub ]
%SER 79.06 [ 1661 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_14
%WER 47.76 [ 5127 / 10735, 674 ins, 820 del, 3633 sub ]
%SER 78.82 [ 1656 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_15
%WER 47.54 [ 5103 / 10735, 636 ins, 855 del, 3612 sub ]
%SER 78.91 [ 1658 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_16
%WER 47.51 [ 5100 / 10735, 583 ins, 904 del, 3613 sub ]
%SER 78.77 [ 1655 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_17
%WER 47.76 [ 5127 / 10735, 558 ins, 938 del, 3631 sub ]
%SER 78.91 [ 1658 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_7
%WER 54.87 [ 5890 / 10735, 1276 ins, 579 del, 4035 sub ]
%SER 82.91 [ 1742 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_8
%WER 53.08 [ 5698 / 10735, 1136 ins, 611 del, 3951 sub ]
%SER 82.01 [ 1723 / 2101 ]
exp/tri3b/decode_tgsmall_test/wer_9
%WER 51.48 [ 5526 / 10735, 1006 ins, 660 del, 3860 sub ]
%SER 81.20 [ 1706 / 2101 ]
****** lmrescore.sh ******
steps/lmrescore.sh --cmd run.pl --mem 4G data/lang_test_tgsmall data/lang_test_tgmed data/test exp/tri3b/decode_tgsmall_test exp/tri3b/decode_tgmed_test
exp/tri3b/decode_tgmed_test/wer_10
%WER 49.41 [ 5297 / 10720, 837 ins, 724 del, 3736 sub ] [PARTIAL]
%SER 79.69 [ 1671 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_11
%WER 48.64 [ 5214 / 10720, 769 ins, 744 del, 3701 sub ] [PARTIAL]
%SER 79.54 [ 1668 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_12
%WER 48.01 [ 5147 / 10720, 714 ins, 783 del, 3650 sub ] [PARTIAL]
%SER 79.21 [ 1661 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_13
%WER 47.71 [ 5115 / 10720, 659 ins, 812 del, 3644 sub ] [PARTIAL]
%SER 78.87 [ 1654 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_14
%WER 47.60 [ 5103 / 10720, 619 ins, 849 del, 3635 sub ] [PARTIAL]
%SER 78.78 [ 1652 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_15
%WER 47.41 [ 5082 / 10720, 589 ins, 885 del, 3608 sub ] [PARTIAL]
%SER 78.87 [ 1654 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_16
%WER 47.52 [ 5094 / 10720, 556 ins, 951 del, 3587 sub ] [PARTIAL]
%SER 78.73 [ 1651 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_17
%WER 47.76 [ 5120 / 10720, 535 ins, 982 del, 3603 sub ] [PARTIAL]
%SER 78.83 [ 1653 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_7
%WER 53.89 [ 5777 / 10720, 1157 ins, 603 del, 4017 sub ] [PARTIAL]
%SER 82.31 [ 1726 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_8
%WER 52.20 [ 5596 / 10720, 1028 ins, 637 del, 3931 sub ] [PARTIAL]
%SER 81.50 [ 1709 / 2097 ]
exp/tri3b/decode_tgmed_test/wer_9
%WER 50.58 [ 5422 / 10720, 906 ins, 676 del, 3840 sub ] [PARTIAL]
%SER 80.40 [ 1686 / 2097 ]
****** lmrescore_const_arpa.sh ******
steps/lmrescore_const_arpa.sh --cmd run.pl --mem 4G data/lang_test_tgsmall data/lang_test_tglarge data/test exp/tri3b/decode_tgsmall_test exp/tri3b/decode_tglarge_test
exp/tri3b/decode_tglarge_test/wer_10
%WER 49.42 [ 5305 / 10735, 837 ins, 726 del, 3742 sub ]
%SER 79.68 [ 1674 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_11
%WER 48.64 [ 5221 / 10735, 767 ins, 745 del, 3709 sub ]
%SER 79.53 [ 1671 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_12
%WER 48.06 [ 5159 / 10735, 717 ins, 784 del, 3658 sub ]
%SER 79.20 [ 1664 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_13
%WER 47.73 [ 5124 / 10735, 661 ins, 812 del, 3651 sub ]
%SER 78.87 [ 1657 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_14
%WER 47.63 [ 5113 / 10735, 623 ins, 849 del, 3641 sub ]
%SER 78.72 [ 1654 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_15
%WER 47.45 [ 5094 / 10735, 590 ins, 886 del, 3618 sub ]
%SER 78.91 [ 1658 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_16
%WER 47.52 [ 5101 / 10735, 555 ins, 955 del, 3591 sub ]
%SER 78.77 [ 1655 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_17
%WER 47.76 [ 5127 / 10735, 533 ins, 983 del, 3611 sub ]
%SER 78.87 [ 1657 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_7
%WER 53.94 [ 5790 / 10735, 1159 ins, 605 del, 4026 sub ]
%SER 82.29 [ 1729 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_8
%WER 52.24 [ 5608 / 10735, 1029 ins, 639 del, 3940 sub ]
%SER 81.49 [ 1712 / 2101 ]
exp/tri3b/decode_tglarge_test/wer_9
%WER 50.61 [ 5433 / 10735, 908 ins, 684 del, 3841 sub ]
%SER 80.39 [ 1689 / 2101 ]

===== STAGE 10 =====
==== Train a chain model ====

local/chain/run_tdnn_1j_short.sh 
local/nnet3/run_ivector_common.sh: preparing directory for low-resolution speed-perturbed data (for alignment)
fix_data_dir.sh: kept all 10647 utterances.
fix_data_dir.sh: old files are kept in data/train/.backup
utils/data/perturb_data_dir_speed_3way.sh: making sure the utt2dur and the reco2dur files are present
... in data/train, because obtaining it after speed-perturbing
... would be very slow, and you might need them.
utils/data/get_utt2dur.sh: data/train/utt2dur already exists with the expected length.  We won't recompute it.
utils/data/get_reco2dur.sh: obtaining durations from recordings
utils/data/get_reco2dur.sh: could not get recording lengths from sphere-file headers, using wav-to-duration
utils/data/get_reco2dur.sh: computed data/train/reco2dur
utils/data/perturb_data_dir_speed.sh: generated speed-perturbed version of data in data/train, in data/train_sp_speed0.9
fix_data_dir.sh: kept all 10647 utterances.
fix_data_dir.sh: old files are kept in data/train_sp_speed0.9/.backup
utils/validate_data_dir.sh: Successfully validated data-directory data/train_sp_speed0.9
utils/data/perturb_data_dir_speed.sh: generated speed-perturbed version of data in data/train, in data/train_sp_speed1.1
fix_data_dir.sh: kept all 10647 utterances.
fix_data_dir.sh: old files are kept in data/train_sp_speed1.1/.backup
utils/validate_data_dir.sh: Successfully validated data-directory data/train_sp_speed1.1
utils/data/combine_data.sh data/train_sp data/train data/train_sp_speed0.9 data/train_sp_speed1.1
utils/data/combine_data.sh: combined utt2uniq
utils/data/combine_data.sh: combined segments
utils/data/combine_data.sh: combined utt2spk
utils/data/combine_data.sh [info]: not combining utt2lang as it does not exist
utils/data/combine_data.sh: combined utt2dur
utils/data/combine_data.sh [info]: **not combining utt2num_frames as it does not exist everywhere**
utils/data/combine_data.sh: combined reco2dur
utils/data/combine_data.sh [info]: **not combining feats.scp as it does not exist everywhere**
utils/data/combine_data.sh: combined text
utils/data/combine_data.sh [info]: **not combining cmvn.scp as it does not exist everywhere**
utils/data/combine_data.sh [info]: not combining vad.scp as it does not exist
utils/data/combine_data.sh [info]: not combining reco2file_and_channel as it does not exist
utils/data/combine_data.sh: combined wav.scp
utils/data/combine_data.sh: combined spk2gender
fix_data_dir.sh: kept all 31941 utterances.
fix_data_dir.sh: old files are kept in data/train_sp/.backup
utils/data/perturb_data_dir_speed_3way.sh: generated 3-way speed-perturbed version of data in data/train, in data/train_sp
utils/validate_data_dir.sh: Successfully validated data-directory data/train_sp
local/nnet3/run_ivector_common.sh: making MFCC features for low-resolution speed-perturbed data
steps/make_mfcc.sh --cmd run.pl --mem 2G --nj 1 data/train_sp
utils/validate_data_dir.sh: Successfully validated data-directory data/train_sp
steps/make_mfcc.sh [info]: segments file exists: using that.
steps/make_mfcc.sh: Succeeded creating MFCC features for train_sp
steps/compute_cmvn_stats.sh data/train_sp
Succeeded creating CMVN stats for train_sp
fix_data_dir.sh: kept all 31941 utterances.
fix_data_dir.sh: old files are kept in data/train_sp/.backup
local/nnet3/run_ivector_common.sh: aligning with the perturbed low-resolution data
steps/align_fmllr.sh --nj 1 --cmd run.pl --mem 2G data/train_sp data/lang exp/tri3b exp/tri3b_ali_train_sp
steps/align_fmllr.sh: feature type is lda
steps/align_fmllr.sh: compiling training graphs
steps/align_fmllr.sh: aligning data in data/train_sp using exp/tri3b/final.alimdl and speaker-independent features.
steps/align_fmllr.sh: computing fMLLR transforms
steps/align_fmllr.sh: doing final alignment.
steps/align_fmllr.sh: done aligning data.
steps/diagnostic/analyze_alignments.sh --cmd run.pl --mem 2G data/lang exp/tri3b_ali_train_sp
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3b_ali_train_sp/log/analyze_alignments.log
61 warnings in exp/tri3b_ali_train_sp/log/fmllr.*.log
535 warnings in exp/tri3b_ali_train_sp/log/align_pass1.*.log
381 warnings in exp/tri3b_ali_train_sp/log/align_pass2.*.log
local/nnet3/run_ivector_common.sh: creating high-resolution MFCC features
utils/copy_data_dir.sh: copied data from data/train_sp to data/train_sp_hires
utils/validate_data_dir.sh: Successfully validated data-directory data/train_sp_hires
utils/copy_data_dir.sh: copied data from data/test to data/test_hires
utils/validate_data_dir.sh: Successfully validated data-directory data/test_hires
utils/data/perturb_data_dir_volume.sh: data/train_sp_hires/feats.scp exists; moving it to data/train_sp_hires/.backup/ as it wouldn't be valid any more.
utils/data/perturb_data_dir_volume.sh: added volume perturbation to the data in data/train_sp_hires
steps/make_mfcc.sh --nj 1 --mfcc-config conf/mfcc_hires.conf --cmd run.pl --mem 2G data/train_sp_hires
utils/validate_data_dir.sh: Successfully validated data-directory data/train_sp_hires
steps/make_mfcc.sh [info]: segments file exists: using that.
steps/make_mfcc.sh: Succeeded creating MFCC features for train_sp_hires
steps/compute_cmvn_stats.sh data/train_sp_hires
Succeeded creating CMVN stats for train_sp_hires
fix_data_dir.sh: kept all 31941 utterances.
fix_data_dir.sh: old files are kept in data/train_sp_hires/.backup
steps/make_mfcc.sh --nj 1 --mfcc-config conf/mfcc_hires.conf --cmd run.pl --mem 2G data/test_hires
steps/make_mfcc.sh: moving data/test_hires/feats.scp to data/test_hires/.backup
utils/validate_data_dir.sh: Successfully validated data-directory data/test_hires
steps/make_mfcc.sh [info]: segments file exists: using that.
steps/make_mfcc.sh: Succeeded creating MFCC features for test_hires
steps/compute_cmvn_stats.sh data/test_hires
Succeeded creating CMVN stats for test_hires
fix_data_dir.sh: kept all 2101 utterances.
fix_data_dir.sh: old files are kept in data/test_hires/.backup
local/nnet3/run_ivector_common.sh: computing a subset of data to train the diagonal UBM.
utils/data/subset_data_dir.sh: reducing #utt from 31941 to 7985
local/nnet3/run_ivector_common.sh: computing a PCA transform from the hires data.
steps/online/nnet2/get_pca_transform.sh --cmd run.pl --mem 2G --splice-opts --left-context=3 --right-context=3 --max-utts 10000 --subsample 2 exp/nnet3/diag_ubm/train_sp_hires_subset exp/nnet3/pca_transform
Done estimating PCA transform in exp/nnet3/pca_transform
local/nnet3/run_ivector_common.sh: training the diagonal UBM.
steps/online/nnet2/train_diag_ubm.sh --cmd run.pl --mem 2G --nj 1 --num-frames 700000 --num-threads 8 exp/nnet3/diag_ubm/train_sp_hires_subset 512 exp/nnet3/pca_transform exp/nnet3/diag_ubm
steps/online/nnet2/train_diag_ubm.sh: Directory exp/nnet3/diag_ubm already exists. Backing up diagonal UBM in exp/nnet3/diag_ubm/backup.bmM
steps/online/nnet2/train_diag_ubm.sh: initializing model from E-M in memory, 
steps/online/nnet2/train_diag_ubm.sh: starting from 256 Gaussians, reaching 512;
steps/online/nnet2/train_diag_ubm.sh: for 20 iterations, using at most 700000 frames of data
Getting Gaussian-selection info
steps/online/nnet2/train_diag_ubm.sh: will train for 4 iterations, in parallel over
steps/online/nnet2/train_diag_ubm.sh: 1 machines, parallelized with 'run.pl --mem 2G'
steps/online/nnet2/train_diag_ubm.sh: Training pass 0
steps/online/nnet2/train_diag_ubm.sh: Training pass 1
steps/online/nnet2/train_diag_ubm.sh: Training pass 2
steps/online/nnet2/train_diag_ubm.sh: Training pass 3
local/nnet3/run_ivector_common.sh: training the iVector extractor
steps/online/nnet2/train_ivector_extractor.sh --cmd run.pl --mem 2G --nj 1 --num-threads 4 --num-processes 2 --online-cmvn-iextractor false data/train_sp_hires exp/nnet3/diag_ubm exp/nnet3/extractor
steps/online/nnet2/train_ivector_extractor.sh: doing Gaussian selection and posterior computation
Accumulating stats (pass 0)
Summing accs (pass 0)
Updating model (pass 0)
Accumulating stats (pass 1)
Summing accs (pass 1)
Updating model (pass 1)
Accumulating stats (pass 2)
Summing accs (pass 2)
Updating model (pass 2)
Accumulating stats (pass 3)
Summing accs (pass 3)
Updating model (pass 3)
Accumulating stats (pass 4)
Summing accs (pass 4)
Updating model (pass 4)
Accumulating stats (pass 5)
Summing accs (pass 5)
Updating model (pass 5)
Accumulating stats (pass 6)
Summing accs (pass 6)
Updating model (pass 6)
Accumulating stats (pass 7)
Summing accs (pass 7)
Updating model (pass 7)
Accumulating stats (pass 8)
Summing accs (pass 8)
Updating model (pass 8)
Accumulating stats (pass 9)
Summing accs (pass 9)
Updating model (pass 9)
utils/data/modify_speaker_info.sh: copied data from data/train_sp_hires to exp/nnet3/ivectors_train_sp_hires/train_sp_hires_max2, number of speakers changed from 423 to 16092
utils/validate_data_dir.sh: Successfully validated data-directory exp/nnet3/ivectors_train_sp_hires/train_sp_hires_max2
steps/online/nnet2/extract_ivectors_online.sh --cmd run.pl --mem 2G --nj 1 exp/nnet3/ivectors_train_sp_hires/train_sp_hires_max2 exp/nnet3/extractor exp/nnet3/ivectors_train_sp_hires
steps/online/nnet2/extract_ivectors_online.sh: extracting iVectors
steps/online/nnet2/extract_ivectors_online.sh: combining iVectors across jobs
steps/online/nnet2/extract_ivectors_online.sh: done extracting (online) iVectors to exp/nnet3/ivectors_train_sp_hires using the extractor in exp/nnet3/extractor.
steps/online/nnet2/extract_ivectors_online.sh --cmd run.pl --mem 2G --nj 1 data/test_hires exp/nnet3/extractor exp/nnet3/ivectors_test_hires
steps/online/nnet2/extract_ivectors_online.sh: extracting iVectors
steps/online/nnet2/extract_ivectors_online.sh: combining iVectors across jobs
steps/online/nnet2/extract_ivectors_online.sh: done extracting (online) iVectors to exp/nnet3/ivectors_test_hires using the extractor in exp/nnet3/extractor.
local/chain/run_tdnn_1j_short.sh: creating lang directory data/lang_chain with chain-type topology

====== STAGE 11 ======
steps/align_fmllr_lats.sh --nj 4 --cmd run.pl --mem 2G data/train_sp data/lang exp/tri3b exp/chain/tri3b_train_sp_lats
steps/align_fmllr_lats.sh: feature type is lda
steps/align_fmllr_lats.sh: compiling training graphs
steps/align_fmllr_lats.sh: aligning data in data/train_sp using exp/tri3b/final.alimdl and speaker-independent features.
steps/align_fmllr_lats.sh: computing fMLLR transforms
steps/align_fmllr_lats.sh: generating lattices containing alternate pronunciations.
steps/align_fmllr_lats.sh: done generating lattices from training transcripts.
62 warnings in exp/chain/tri3b_train_sp_lats/log/fmllr.*.log
31 warnings in exp/chain/tri3b_train_sp_lats/log/generate_lattices.*.log
553 warnings in exp/chain/tri3b_train_sp_lats/log/align_pass1.*.log

====== STAGE 12 ======
steps/nnet3/chain/build_tree.sh --frame-subsampling-factor 3 --context-opts --context-width=2 --central-position=1 --cmd run.pl --mem 2G 3500 data/train_sp data/lang_chain exp/tri3b_ali_train_sp exp/chain/tree_sp
steps/nnet3/chain/build_tree.sh: feature type is lda
steps/nnet3/chain/build_tree.sh: Using transforms from exp/tri3b_ali_train_sp
steps/nnet3/chain/build_tree.sh: Initializing monophone model (for alignment conversion, in case topology changed)
steps/nnet3/chain/build_tree.sh: Accumulating tree stats
steps/nnet3/chain/build_tree.sh: Getting questions for tree clustering.
steps/nnet3/chain/build_tree.sh: Building the tree
steps/nnet3/chain/build_tree.sh: Initializing the model
WARNING (gmm-init-model[5.5.1060~1-ae8cb]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 1 with no stats; corresponding phone list: 6 7 8 9 10 
This is a bad warning.
steps/nnet3/chain/build_tree.sh: Converting alignments from exp/tri3b_ali_train_sp to use current tree
steps/nnet3/chain/build_tree.sh: Done building tree

====== STAGE 13 ======
local/chain/run_tdnn_1j_short.sh: creating neural net configs using the xconfig parser

====== STAGE 14 ======
steps/nnet3/chain/get_egs.sh --frames-overlap-per-eg 0 --cmd run.pl --mem 4G --cmvn-opts --norm-means=false --norm-vars=false --online-ivector-dir exp/nnet3/ivectors_train_sp_hires --left-context 24 --right-context 24 --left-context-initial -1 --right-context-final -1 --left-tolerance 5 --right-tolerance 5 --frame-subsampling-factor 3 --alignment-subsampling-factor 3 --stage 0 --frames-per-iter 3000000 --frames-per-eg 140,100,160 --srand 0 data/train_sp_hires exp/chain/tdnn1j_sp exp/chain/tri3b_train_sp_lats exp/chain/tdnn1j_sp/egs
steps/nnet3/chain/get_egs.sh: File data/train_sp_hires/utt2uniq exists, so ensuring the hold-out set includes all perturbed versions of the same source utterance.
steps/nnet3/chain/get_egs.sh: Holding out 300 utterances in validation set and 300 in training diagnostic set, out of total 31941.
steps/nnet3/chain/get_egs.sh: creating egs.  To ensure they are not deleted later you can do:  touch exp/chain/tdnn1j_sp/egs/.nodelete
steps/nnet3/chain/get_egs.sh: feature type is raw, with 'apply-cmvn'
steps/nnet3/chain/get_egs.sh: working out number of frames of training data
steps/nnet3/chain/get_egs.sh: working out feature dim
steps/nnet3/chain/get_egs.sh: creating 5 archives, each with 18149 egs, with
steps/nnet3/chain/get_egs.sh:   140,100,160 labels per example, and (left,right) context = (24,24)
steps/nnet3/chain/get_egs.sh: Getting validation and training subset examples in background.
steps/nnet3/chain/get_egs.sh: Generating training examples on disk
steps/nnet3/chain/get_egs.sh: Getting subsets of validation examples for diagnostics and combination.
steps/nnet3/chain/get_egs.sh: recombining and shuffling order of archives on disk
steps/nnet3/chain/get_egs.sh: Removing temporary archives, alignments and lattices
steps/nnet3/chain/get_egs.sh: Finished preparing training examples
steps/nnet2/remove_egs.sh: Finished deleting examples in exp/chain/tdnn1j_sp/egs
exp/chain/tdnn1j_sp: num-iters=150 nj=2..2 num-params=4.7M dim=40+100->2536 combine=-0.151->-0.142 (over 5) xent:train/valid[99,149]=(-2.64,-2.47/-2.59,-2.45) logprob:train/valid[99,149]=(-0.157,-0.143/-0.155,-0.142)
steps/nnet3/chain/train.py --stage=-10 --cmd=run.pl --mem 4G --feat.online-ivector-dir=exp/nnet3/ivectors_train_sp_hires --feat.cmvn-opts=--norm-means=false --norm-vars=false --chain.xent-regularize 0.1 --chain.leaky-hmm-coefficient=0.1 --chain.l2-regularize=0.0 --chain.apply-deriv-weights=false --chain.lm-opts=--num-extra-lm-states=2000 --trainer.add-option=--optimization.memory-compression-level=2 --trainer.srand=0 --trainer.max-param-change=2.0 --trainer.num-epochs=20 --trainer.frames-per-iter=3000000 --trainer.optimization.num-jobs-initial=2 --trainer.optimization.num-jobs-final=2 --trainer.optimization.initial-effective-lrate=0.002 --trainer.optimization.final-effective-lrate=0.0002 --trainer.num-chunk-per-minibatch=128,64 --egs.chunk-width=140,100,160 --egs.dir= --egs.opts=--frames-overlap-per-eg 0 --cleanup.remove-egs=true --use-gpu=wait --reporting.email= --feat-dir=data/train_sp_hires --tree-dir=exp/chain/tree_sp --lat-dir=exp/chain/tri3b_train_sp_lats --dir=exp/chain/tdnn1j_sp
['steps/nnet3/chain/train.py', '--stage=-10', '--cmd=run.pl --mem 4G', '--feat.online-ivector-dir=exp/nnet3/ivectors_train_sp_hires', '--feat.cmvn-opts=--norm-means=false --norm-vars=false', '--chain.xent-regularize', '0.1', '--chain.leaky-hmm-coefficient=0.1', '--chain.l2-regularize=0.0', '--chain.apply-deriv-weights=false', '--chain.lm-opts=--num-extra-lm-states=2000', '--trainer.add-option=--optimization.memory-compression-level=2', '--trainer.srand=0', '--trainer.max-param-change=2.0', '--trainer.num-epochs=20', '--trainer.frames-per-iter=3000000', '--trainer.optimization.num-jobs-initial=2', '--trainer.optimization.num-jobs-final=2', '--trainer.optimization.initial-effective-lrate=0.002', '--trainer.optimization.final-effective-lrate=0.0002', '--trainer.num-chunk-per-minibatch=128,64', '--egs.chunk-width=140,100,160', '--egs.dir=', '--egs.opts=--frames-overlap-per-eg 0', '--cleanup.remove-egs=true', '--use-gpu=wait', '--reporting.email=', '--feat-dir=data/train_sp_hires', '--tree-dir=exp/chain/tree_sp', '--lat-dir=exp/chain/tri3b_train_sp_lats', '--dir=exp/chain/tdnn1j_sp']

====== STAGE 15 ======
-0.0633072 -0.0641278
[info]: CLG not stochastic.
0.56177 -0.244337
HCLGa is not stochastic
0.478711 -0.186665
[info]: final HCLG is not stochastic.

====== STAGE 16 ======
steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 --frames-per-chunk 140 --nj 108 --cmd run.pl --mem 4G --num-threads 4 --online-ivector-dir exp/nnet3/ivectors_test_hires exp/chain/tree_sp/graph_tgsmall data/test_hires exp/chain/tdnn1j_sp/decode_tgsmall_test
steps/nnet3/decode.sh: feature type is raw
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 4G --iter final exp/chain/tree_sp/graph_tgsmall exp/chain/tdnn1j_sp/decode_tgsmall_test
steps/diagnostic/analyze_lats.sh: see stats in exp/chain/tdnn1j_sp/decode_tgsmall_test/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(2,19,202) and mean=76.3
steps/diagnostic/analyze_lats.sh: see stats in exp/chain/tdnn1j_sp/decode_tgsmall_test/log/analyze_lattice_depth_stats.log
score best paths
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_10
%WER 34.40 [ 3693 / 10735, 307 ins, 641 del, 2745 sub ]
%SER 68.25 [ 1434 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_11
%WER 34.76 [ 3732 / 10735, 280 ins, 688 del, 2764 sub ]
%SER 68.78 [ 1445 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_12
%WER 35.77 [ 3840 / 10735, 274 ins, 744 del, 2822 sub ]
%SER 69.87 [ 1468 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_13
%WER 36.32 [ 3899 / 10735, 260 ins, 779 del, 2860 sub ]
%SER 71.11 [ 1494 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_14
%WER 37.08 [ 3981 / 10735, 246 ins, 830 del, 2905 sub ]
%SER 71.78 [ 1508 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_15
%WER 38.12 [ 4092 / 10735, 241 ins, 882 del, 2969 sub ]
%SER 72.82 [ 1530 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_16
%WER 39.12 [ 4199 / 10735, 229 ins, 946 del, 3024 sub ]
%SER 73.87 [ 1552 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_17
%WER 39.79 [ 4271 / 10735, 220 ins, 975 del, 3076 sub ]
%SER 74.68 [ 1569 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_7
%WER 35.15 [ 3773 / 10735, 399 ins, 555 del, 2819 sub ]
%SER 68.11 [ 1431 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_8
%WER 34.46 [ 3699 / 10735, 354 ins, 584 del, 2761 sub ]
%SER 67.78 [ 1424 / 2101 ]
exp/chain/tdnn1j_sp/decode_tgsmall_test/wer_9
%WER 34.31 [ 3683 / 10735, 331 ins, 629 del, 2723 sub ]
%SER 68.06 [ 1430 / 2101 ]
score confidence and timing with sclite
Decoding done.
steps/lmrescore_const_arpa.sh --cmd run.pl --mem 4G data/lang_test_tgsmall data/lang_test_tglarge data/test_hires exp/chain/tdnn1j_sp/decode_tgsmall_test exp/chain/tdnn1j_sp/decode_tglarge_test
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_10
%WER 34.49 [ 3703 / 10735, 279 ins, 673 del, 2751 sub ]
%SER 68.40 [ 1437 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_11
%WER 34.69 [ 3724 / 10735, 258 ins, 714 del, 2752 sub ]
%SER 68.97 [ 1449 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_12
%WER 35.57 [ 3818 / 10735, 254 ins, 769 del, 2795 sub ]
%SER 69.87 [ 1468 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_13
%WER 36.39 [ 3907 / 10735, 243 ins, 813 del, 2851 sub ]
%SER 70.97 [ 1491 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_14
%WER 37.35 [ 4010 / 10735, 234 ins, 882 del, 2894 sub ]
%SER 71.87 [ 1510 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_15
%WER 38.43 [ 4125 / 10735, 225 ins, 940 del, 2960 sub ]
%SER 73.01 [ 1534 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_16
%WER 39.52 [ 4242 / 10735, 221 ins, 996 del, 3025 sub ]
%SER 74.11 [ 1557 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_17
%WER 39.96 [ 4290 / 10735, 215 ins, 1031 del, 3044 sub ]
%SER 74.63 [ 1568 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_7
%WER 34.91 [ 3748 / 10735, 370 ins, 578 del, 2800 sub ]
%SER 68.02 [ 1429 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_8
%WER 34.36 [ 3689 / 10735, 324 ins, 621 del, 2744 sub ]
%SER 67.82 [ 1425 / 2101 ]
exp/chain/tdnn1j_sp/decode_tglarge_test/wer_9
%WER 34.32 [ 3684 / 10735, 302 ins, 654 del, 2728 sub ]
%SER 68.11 [ 1431 / 2101 ]

====== STAGE 17 ======
steps/online/nnet3/prepare_online_decoding.sh --mfcc-config conf/mfcc_hires.conf data/lang_chain exp/nnet3/extractor exp/chain/tdnn1j_sp exp/chain/tdnn1j_sp_online
steps/online/nnet3/prepare_online_decoding.sh: preparing configuration files in /home/gweltaz/STT/kaldi/egs/bzg/exp/chain/tdnn1j_sp_online/conf
steps/online/nnet3/prepare_online_decoding.sh: created config file /home/gweltaz/STT/kaldi/egs/bzg/exp/chain/tdnn1j_sp_online/conf/online.conf
steps/online/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 --nj 108 --cmd run.pl --mem 4G exp/chain/tree_sp/graph_tgsmall data/test exp/chain/tdnn1j_sp_online/decode_tgsmall_test
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_10
%WER 34.34 [ 3686 / 10735, 301 ins, 656 del, 2729 sub ]
%SER 68.54 [ 1440 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_11
%WER 34.72 [ 3727 / 10735, 273 ins, 700 del, 2754 sub ]
%SER 68.78 [ 1445 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_12
%WER 35.55 [ 3816 / 10735, 274 ins, 741 del, 2801 sub ]
%SER 69.87 [ 1468 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_13
%WER 36.13 [ 3879 / 10735, 257 ins, 787 del, 2835 sub ]
%SER 71.06 [ 1493 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_14
%WER 37.07 [ 3979 / 10735, 253 ins, 831 del, 2895 sub ]
%SER 71.73 [ 1507 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_15
%WER 37.81 [ 4059 / 10735, 233 ins, 863 del, 2963 sub ]
%SER 72.73 [ 1528 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_16
%WER 38.79 [ 4164 / 10735, 234 ins, 910 del, 3020 sub ]
%SER 73.63 [ 1547 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_17
%WER 39.52 [ 4243 / 10735, 234 ins, 943 del, 3066 sub ]
%SER 74.63 [ 1568 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_7
%WER 35.08 [ 3766 / 10735, 387 ins, 554 del, 2825 sub ]
%SER 68.16 [ 1432 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_8
%WER 34.40 [ 3693 / 10735, 342 ins, 586 del, 2765 sub ]
%SER 67.68 [ 1422 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tgsmall_test/wer_9
%WER 34.13 [ 3664 / 10735, 322 ins, 624 del, 2718 sub ]
%SER 67.97 [ 1428 / 2101 ]
steps/lmrescore_const_arpa.sh --cmd run.pl --mem 4G data/lang_test_tgsmall data/lang_test_tglarge data/test_hires exp/chain/tdnn1j_sp_online/decode_tgsmall_test exp/chain/tdnn1j_sp_online/decode_tglarge_test
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_10
%WER 34.39 [ 3692 / 10735, 278 ins, 685 del, 2729 sub ]
%SER 68.54 [ 1440 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_11
%WER 34.75 [ 3730 / 10735, 257 ins, 727 del, 2746 sub ]
%SER 69.01 [ 1450 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_12
%WER 35.56 [ 3817 / 10735, 259 ins, 771 del, 2787 sub ]
%SER 69.92 [ 1469 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_13
%WER 36.17 [ 3883 / 10735, 247 ins, 813 del, 2823 sub ]
%SER 70.82 [ 1488 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_14
%WER 37.26 [ 4000 / 10735, 237 ins, 872 del, 2891 sub ]
%SER 71.63 [ 1505 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_15
%WER 38.03 [ 4083 / 10735, 225 ins, 907 del, 2951 sub ]
%SER 72.68 [ 1527 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_16
%WER 38.96 [ 4182 / 10735, 227 ins, 951 del, 3004 sub ]
%SER 73.73 [ 1549 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_17
%WER 39.62 [ 4253 / 10735, 229 ins, 984 del, 3040 sub ]
%SER 74.49 [ 1565 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_7
%WER 34.90 [ 3747 / 10735, 365 ins, 580 del, 2802 sub ]
%SER 68.02 [ 1429 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_8
%WER 34.48 [ 3701 / 10735, 319 ins, 627 del, 2755 sub ]
%SER 67.68 [ 1422 / 2101 ]
exp/chain/tdnn1j_sp_online/decode_tglarge_test/wer_9
%WER 34.33 [ 3685 / 10735, 307 ins, 651 del, 2727 sub ]
%SER 68.16 [ 1432 / 2101 ]

===== run.sh script is finished =====

