/opt/pkg/kaldi/egs/thchs30/s5
root@lambda-Precision-3510:/opt/pkg/kaldi/egs/thchs30/s5# sh run.sh
creating data/{train,dev,test}
cleaning data/train
preparing scps and text in data/train
cleaning data/dev
preparing scps and text in data/dev
cleaning data/test
preparing scps and text in data/test
creating test_phone for phone decoding
steps/make_mfcc.sh --nj 8 --cmd run.pl data/mfcc/train exp/make_mfcc/train mfcc/train
utils/validate_data_dir.sh: Successfully validated data-directory data/mfcc/train
steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating MFCC features for train
steps/compute_cmvn_stats.sh data/mfcc/train exp/mfcc_cmvn/train mfcc/train
Succeeded creating CMVN stats for train
steps/make_mfcc.sh --nj 8 --cmd run.pl data/mfcc/dev exp/make_mfcc/dev mfcc/dev
utils/validate_data_dir.sh: Successfully validated data-directory data/mfcc/dev
steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating MFCC features for dev
steps/compute_cmvn_stats.sh data/mfcc/dev exp/mfcc_cmvn/dev mfcc/dev
Succeeded creating CMVN stats for dev
steps/make_mfcc.sh --nj 8 --cmd run.pl data/mfcc/test exp/make_mfcc/test mfcc/test
utils/validate_data_dir.sh: Successfully validated data-directory data/mfcc/test
steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating MFCC features for test
steps/compute_cmvn_stats.sh data/mfcc/test exp/mfcc_cmvn/test mfcc/test
Succeeded creating CMVN stats for test
make word graph ...
utils/prepare_lang.sh --position_dependent_phones false data/dict <SPOKEN_NOISE> data/local/lang data/lang
Checking data/dict/silence_phones.txt ...
--> reading data/dict/silence_phones.txt
--> data/dict/silence_phones.txt is OK
Checking data/dict/optional_silence.txt ...
--> reading data/dict/optional_silence.txt
--> data/dict/optional_silence.txt is OK
Checking data/dict/nonsilence_phones.txt ...
--> reading data/dict/nonsilence_phones.txt
--> data/dict/nonsilence_phones.txt is OK
Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.
Checking data/dict/lexicon.txt
--> reading data/dict/lexicon.txt
--> data/dict/lexicon.txt is OK
Checking data/dict/extra_questions.txt ...
--> reading data/dict/extra_questions.txt
--> data/dict/extra_questions.txt is OK
--> SUCCESS [validating dictionary directory data/dict]
**Creating data/dict/lexiconp.txt from data/dict/lexicon.txt
fstaddselfloops data/lang/phones/wdisambig_phones.int data/lang/phones/wdisambig_words.int
prepare_lang.sh: validating output directory
utils/validate_lang.pl data/lang
Checking data/lang/phones.txt ...
--> data/lang/phones.txt is OK
Checking words.txt: #0 ...
--> 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 ...
--> summation property is OK
Checking data/lang/phones/context_indep.{txt, int, csl} ...
--> 1 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} ...
--> 217 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} ...
--> 1 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} ...
--> 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} ...
--> 57 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} ...
--> 218 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} ...
--> 218 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} ...
--> 7 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 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-level disambiguation symbols...
--> data/lang/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking data/lang/oov.{txt, int} ...
--> 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]
Converting 'data/graph/word.3gram.lm.gz' to FST
arpa2fst --disambig-symbol=#0 --read-symbol-table=data/graph/lang/words.txt - data/graph/lang/G.fst
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:96) Reading \data\ section.
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:151) Reading \1-grams: section.
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:151) Reading \2-grams: section.
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:151) Reading \3-grams: section.
LOG (arpa2fst[5.1.4-7d53]:RemoveRedundantStates():arpa-lm-compiler.cc:355) Reduced num-states from 3076353 to 454251
fstisstochastic data/graph/lang/G.fst
8.99409e-06 -0.832396
Succeeded in formatting LM: 'data/graph/word.3gram.lm.gz'
make phone graph ...
utils/prepare_lang.sh --position_dependent_phones false data/dict_phone <SPOKEN_NOISE> data/local/lang_phone data/lang_phone
Checking data/dict_phone/silence_phones.txt ...
--> reading data/dict_phone/silence_phones.txt
--> data/dict_phone/silence_phones.txt is OK
Checking data/dict_phone/optional_silence.txt ...
--> reading data/dict_phone/optional_silence.txt
--> data/dict_phone/optional_silence.txt is OK
Checking data/dict_phone/nonsilence_phones.txt ...
--> reading data/dict_phone/nonsilence_phones.txt
--> data/dict_phone/nonsilence_phones.txt is OK
Checking disjoint: silence_phones.txt, nonsilence_phones.txt
--> disjoint property is OK.
Checking data/dict_phone/lexicon.txt
--> reading data/dict_phone/lexicon.txt
--> data/dict_phone/lexicon.txt is OK
Checking data/dict_phone/extra_questions.txt ...
--> reading data/dict_phone/extra_questions.txt
--> data/dict_phone/extra_questions.txt is OK
--> SUCCESS [validating dictionary directory data/dict_phone]
**Creating data/dict_phone/lexiconp.txt from data/dict_phone/lexicon.txt
fstaddselfloops data/lang_phone/phones/wdisambig_phones.int data/lang_phone/phones/wdisambig_words.int
prepare_lang.sh: validating output directory
utils/validate_lang.pl data/lang_phone
Checking data/lang_phone/phones.txt ...
--> data/lang_phone/phones.txt is OK
Checking words.txt: #0 ...
--> data/lang_phone/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 ...
--> summation property is OK
Checking data/lang_phone/phones/context_indep.{txt, int, csl} ...
--> 1 entry/entries in data/lang_phone/phones/context_indep.txt
--> data/lang_phone/phones/context_indep.int corresponds to data/lang_phone/phones/context_indep.txt
--> data/lang_phone/phones/context_indep.csl corresponds to data/lang_phone/phones/context_indep.txt
--> data/lang_phone/phones/context_indep.{txt, int, csl} are OK
Checking data/lang_phone/phones/nonsilence.{txt, int, csl} ...
--> 217 entry/entries in data/lang_phone/phones/nonsilence.txt
--> data/lang_phone/phones/nonsilence.int corresponds to data/lang_phone/phones/nonsilence.txt
--> data/lang_phone/phones/nonsilence.csl corresponds to data/lang_phone/phones/nonsilence.txt
--> data/lang_phone/phones/nonsilence.{txt, int, csl} are OK
Checking data/lang_phone/phones/silence.{txt, int, csl} ...
--> 1 entry/entries in data/lang_phone/phones/silence.txt
--> data/lang_phone/phones/silence.int corresponds to data/lang_phone/phones/silence.txt
--> data/lang_phone/phones/silence.csl corresponds to data/lang_phone/phones/silence.txt
--> data/lang_phone/phones/silence.{txt, int, csl} are OK
Checking data/lang_phone/phones/optional_silence.{txt, int, csl} ...
--> 1 entry/entries in data/lang_phone/phones/optional_silence.txt
--> data/lang_phone/phones/optional_silence.int corresponds to data/lang_phone/phones/optional_silence.txt
--> data/lang_phone/phones/optional_silence.csl corresponds to data/lang_phone/phones/optional_silence.txt
--> data/lang_phone/phones/optional_silence.{txt, int, csl} are OK
Checking data/lang_phone/phones/disambig.{txt, int, csl} ...
--> 4 entry/entries in data/lang_phone/phones/disambig.txt
--> data/lang_phone/phones/disambig.int corresponds to data/lang_phone/phones/disambig.txt
--> data/lang_phone/phones/disambig.csl corresponds to data/lang_phone/phones/disambig.txt
--> data/lang_phone/phones/disambig.{txt, int, csl} are OK
Checking data/lang_phone/phones/roots.{txt, int} ...
--> 218 entry/entries in data/lang_phone/phones/roots.txt
--> data/lang_phone/phones/roots.int corresponds to data/lang_phone/phones/roots.txt
--> data/lang_phone/phones/roots.{txt, int} are OK
Checking data/lang_phone/phones/sets.{txt, int} ...
--> 218 entry/entries in data/lang_phone/phones/sets.txt
--> data/lang_phone/phones/sets.int corresponds to data/lang_phone/phones/sets.txt
--> data/lang_phone/phones/sets.{txt, int} are OK
Checking data/lang_phone/phones/extra_questions.{txt, int} ...
--> 7 entry/entries in data/lang_phone/phones/extra_questions.txt
--> data/lang_phone/phones/extra_questions.int corresponds to data/lang_phone/phones/extra_questions.txt
--> data/lang_phone/phones/extra_questions.{txt, int} are OK
Checking optional_silence.txt ...
--> reading data/lang_phone/phones/optional_silence.txt
--> data/lang_phone/phones/optional_silence.txt is OK
Checking disambiguation symbols: #0 and #1
--> data/lang_phone/phones/disambig.txt has "#0" and "#1"
--> data/lang_phone/phones/disambig.txt is OK
Checking topo ...
Checking word-level disambiguation symbols...
--> data/lang_phone/phones/wdisambig.txt exists (newer prepare_lang.sh)
Checking data/lang_phone/oov.{txt, int} ...
--> 1 entry/entries in data/lang_phone/oov.txt
--> data/lang_phone/oov.int corresponds to data/lang_phone/oov.txt
--> data/lang_phone/oov.{txt, int} are OK
--> data/lang_phone/L.fst is olabel sorted
--> data/lang_phone/L_disambig.fst is olabel sorted
--> SUCCESS [validating lang directory data/lang_phone]
Converting 'data/graph_phone/phone.3gram.lm.gz' to FST
arpa2fst --disambig-symbol=#0 --read-symbol-table=data/graph_phone/lang/words.txt - data/graph_phone/lang/G.fst
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:96) Reading \data\ section.
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:151) Reading \1-grams: section.
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:151) Reading \2-grams: section.
LOG (arpa2fst[5.1.4-7d53]:Read():arpa-file-parser.cc:151) Reading \3-grams: section.
LOG (arpa2fst[5.1.4-7d53]:RemoveRedundantStates():arpa-lm-compiler.cc:355) Reduced num-states from 5709 to 4848
fstisstochastic data/graph_phone/lang/G.fst
8.25152e-07 -3.76792
Succeeded in formatting LM: 'data/graph_phone/phone.3gram.lm.gz'
steps/train_mono.sh --boost-silence 1.25 --nj 8 --cmd run.pl data/mfcc/train data/lang 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 data/lang exp/mono
steps/diagnostic/analyze_alignments.sh: see stats in exp/mono/log/analyze_alignments.log
1053 warnings in exp/mono/log/update.*.log
3998 warnings in exp/mono/log/align.*.*.log
116 warnings in exp/mono/log/acc.*.*.log
exp/mono: nj=8 align prob=-100.09 over 25.49h [retry=0.2%, fail=0.0%] states=656 gauss=989
steps/train_mono.sh: Done training monophone system in exp/mono
steps/align_si.sh --boost-silence 1.25 --nj 8 --cmd run.pl data/mfcc/train data/lang exp/mono exp/mono_ali
using monophone to generate graph
WARNING: the --mono, --left-biphone and --quinphone options are now deprecated and ignored.
steps/align_si.sh: feature type is delta
steps/align_si.sh: aligning data in data/mfcc/train using model from exp/mono, putting alignments in exp/mono_ali
tree-info exp/mono/tree
tree-info exp/mono/tree
fsttablecompose data/graph/lang/L_disambig.fst data/graph/lang/G.fst
fstminimizeencoded
fstpushspecial
fstdeterminizestar --use-log=true
steps/diagnostic/analyze_alignments.sh --cmd run.pl data/lang exp/mono_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/mono_ali/log/analyze_alignments.log
steps/align_si.sh: done aligning data.
steps/train_deltas.sh --boost-silence 1.25 --cmd run.pl 2000 10000 data/mfcc/train data/lang exp/mono_ali 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[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 109 with no stats; corresponding phone list: 110
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 121 with no stats; corresponding phone list: 122
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 163 with no stats; corresponding phone list: 164
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 175 with no stats; corresponding phone list: 176
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 177 with no stats; corresponding phone list: 178
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 182 with no stats; corresponding phone list: 183
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 203 with no stats; corresponding phone list: 204
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 208 with no stats; corresponding phone list: 209
** 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 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
fstisstochastic data/graph/lang/tmp/LG.fst
-0.0480887 -0.0488874
[info]: LG not stochastic.
fstcomposecontext --context-size=1 --central-position=0 --read-disambig-syms=data/graph/lang/phones/disambig.int --write-disambig-syms=data/graph/lang/tmp/disambig_ilabels_1_0.int data/graph/lang/tmp/ilabels_1_0.23797
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
fstisstochastic data/graph/lang/tmp/CLG_1_0.fst
-0.0480887 -0.0488874
[info]: CLG not stochastic.
make-h-transducer --disambig-syms-out=exp/mono/graph_word/disambig_tid.int --transition-scale=1.0 data/graph/lang/tmp/ilabels_1_0 exp/mono/tree exp/mono/final.mdl
fstrmepslocal
fstminimizeencoded
fstdeterminizestar --use-log=true
fsttablecompose exp/mono/graph_word/Ha.fst data/graph/lang/tmp/CLG_1_0.fst
fstrmsymbols exp/mono/graph_word/disambig_tid.int
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 data/lang exp/tri1
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri1/log/analyze_alignments.log
95 warnings in exp/tri1/log/align.*.*.log
1 warnings in exp/tri1/log/compile_questions.log
1 warnings in exp/tri1/log/build_tree.log
9 warnings in exp/tri1/log/questions.log
9 warnings in exp/tri1/log/init_model.log
281 warnings in exp/tri1/log/update.*.log
79 warnings in exp/tri1/log/acc.*.*.log
exp/tri1: nj=8 align prob=-96.75 over 25.48h [retry=0.4%, fail=0.0%] states=1671 gauss=10024 tree-impr=4.75
steps/train_deltas.sh: Done training system with delta+delta-delta features in exp/tri1
steps/align_si.sh --nj 8 --cmd run.pl data/mfcc/train data/lang exp/tri1 exp/tri1_ali
steps/align_si.sh: feature type is delta
steps/align_si.sh: aligning data in data/mfcc/train using model from exp/tri1, putting alignments in exp/tri1_ali
tree-info exp/tri1/tree
tree-info exp/tri1/tree
fstcomposecontext --context-size=3 --central-position=1 --read-disambig-syms=data/graph/lang/phones/disambig.int --write-disambig-syms=data/graph/lang/tmp/disambig_ilabels_3_1.int data/graph/lang/tmp/ilabels_3_1.30105
steps/diagnostic/analyze_alignments.sh --cmd run.pl data/lang exp/tri1_ali
fstisstochastic data/graph/lang/tmp/CLG_3_1.fst
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri1_ali/log/analyze_alignments.log
steps/align_si.sh: done aligning data.
steps/train_lda_mllt.sh --cmd run.pl --splice-opts --left-context=3 --right-context=3 2500 15000 data/mfcc/train data/lang exp/tri1_ali exp/tri2b
Accumulating LDA statistics.
0 -0.0488874
Accumulating tree stats
[info]: CLG not stochastic.
make-h-transducer --disambig-syms-out=exp/tri1/graph_word/disambig_tid.int --transition-scale=1.0 data/graph/lang/tmp/ilabels_3_1 exp/tri1/tree exp/tri1/final.mdl
fstminimizeencoded
fstrmepslocal
fstdeterminizestar --use-log=true
fstrmsymbols exp/tri1/graph_word/disambig_tid.int
fsttablecompose exp/tri1/graph_word/Ha.fst data/graph/lang/tmp/CLG_3_1.fst
Getting questions for tree clustering.
Building the tree
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstdeterminizestar[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstdeterminizestar() [0x626f94]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmsymbols[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmsymbols() [0x54d84a]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmepslocal[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmepslocal() [0x573986]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstminimizeencoded[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstminimizeencoded() [0x5c3afe]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
steps/train_lda_mllt.sh: Initializing the model
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 109 with no stats; corresponding phone list: 110
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 121 with no stats; corresponding phone list: 122
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 163 with no stats; corresponding phone list: 164
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 175 with no stats; corresponding phone list: 176
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 203 with no stats; corresponding phone list: 204
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 208 with no stats; corresponding phone list: 209
This is a bad warning.
Converting alignments from exp/tri1_ali to use current tree
Compiling graphs of transcripts
Training pass 1
Training pass 2
Estimating MLLT
Training pass 3
Training pass 4
Estimating MLLT
Training pass 5
fstisstochastic exp/mono/graph_word/HCLGa.fst
Training pass 6
Estimating MLLT
0.644531 -0.097426
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/mono/final.mdl
Training pass 7
Training pass 8
Training pass 9
Training pass 10
Aligning data
steps/decode.sh --cmd run.pl --mem 4G --nj 8 exp/mono/graph_word data/mfcc/test exp/mono/decode_test_word
decode.sh: feature type is delta
bash: line 1: 768 Killed ( gmm-latgen-faster --max-active=7000 --beam=13.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/mono/graph_word/words.txt exp/mono/final.mdl exp/mono/graph_word/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/mfcc/test/split8/3/utt2spk scp:data/mfcc/test/split8/3/cmvn.scp scp:data/mfcc/test/split8/3/feats.scp ark:- | add-deltas ark:- ark:- |" "ark:|gzip -c > exp/mono/decode_test_word/lat.3.gz" ) 2>> exp/mono/decode_test_word/log/decode.3.log >> exp/mono/decode_test_word/log/decode.3.log
bash: line 1: 761 Killed ( gmm-latgen-faster --max-active=7000 --beam=13.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/mono/graph_word/words.txt exp/mono/final.mdl exp/mono/graph_word/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/mfcc/test/split8/1/utt2spk scp:data/mfcc/test/split8/1/cmvn.scp scp:data/mfcc/test/split8/1/feats.scp ark:- | add-deltas ark:- ark:- |" "ark:|gzip -c > exp/mono/decode_test_word/lat.1.gz" ) 2>> exp/mono/decode_test_word/log/decode.1.log >> exp/mono/decode_test_word/log/decode.1.log
Training pass 11
bash: line 1: 771 Killed ( gmm-latgen-faster --max-active=7000 --beam=13.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/mono/graph_word/words.txt exp/mono/final.mdl exp/mono/graph_word/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/mfcc/test/split8/4/utt2spk scp:data/mfcc/test/split8/4/cmvn.scp scp:data/mfcc/test/split8/4/feats.scp ark:- | add-deltas ark:- ark:- |" "ark:|gzip -c > exp/mono/decode_test_word/lat.4.gz" ) 2>> exp/mono/decode_test_word/log/decode.4.log >> exp/mono/decode_test_word/log/decode.4.log
bash: line 1: 763 Killed ( gmm-latgen-faster --max-active=7000 --beam=13.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/mono/graph_word/words.txt exp/mono/final.mdl exp/mono/graph_word/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/mfcc/test/split8/5/utt2spk scp:data/mfcc/test/split8/5/cmvn.scp scp:data/mfcc/test/split8/5/feats.scp ark:- | add-deltas ark:- ark:- |" "ark:|gzip -c > exp/mono/decode_test_word/lat.5.gz" ) 2>> exp/mono/decode_test_word/log/decode.5.log >> exp/mono/decode_test_word/log/decode.5.log
Training pass 12
Estimating MLLT
bash: line 1: 764 Killed ( gmm-latgen-faster --max-active=7000 --beam=13.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/mono/graph_word/words.txt exp/mono/final.mdl exp/mono/graph_word/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/mfcc/test/split8/7/utt2spk scp:data/mfcc/test/split8/7/cmvn.scp scp:data/mfcc/test/split8/7/feats.scp ark:- | add-deltas ark:- ark:- |" "ark:|gzip -c > exp/mono/decode_test_word/lat.7.gz" ) 2>> exp/mono/decode_test_word/log/decode.7.log >> exp/mono/decode_test_word/log/decode.7.log
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 data/lang exp/tri2b
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri2b/log/analyze_alignments.log
1 warnings in exp/tri2b/log/build_tree.log
9 warnings in exp/tri2b/log/init_model.log
4 warnings in exp/tri2b/log/lda_acc.*.log
173 warnings in exp/tri2b/log/align.*.*.log
131 warnings in exp/tri2b/log/acc.*.*.log
272 warnings in exp/tri2b/log/update.*.log
7 warnings in exp/tri2b/log/questions.log
1 warnings in exp/tri2b/log/compile_questions.log
exp/tri2b: nj=8 align prob=-48.26 over 25.48h [retry=0.5%, fail=0.0%] states=2112 gauss=15037 tree-impr=4.32 lda-sum=24.00 mllt:impr,logdet=1.21,1.73
Done training system with LDA+MLLT features in exp/tri2b
steps/align_si.sh --nj 8 --cmd run.pl --use-graphs true data/mfcc/train data/lang exp/tri2b exp/tri2b_ali
tree-info exp/tri2b/tree
tree-info exp/tri2b/tree
steps/align_si.sh: feature type is lda
steps/align_si.sh: aligning data in data/mfcc/train using model from exp/tri2b, putting alignments in exp/tri2b_ali
make-h-transducer --disambig-syms-out=exp/tri2b/graph_word/disambig_tid.int --transition-scale=1.0 data/graph/lang/tmp/ilabels_3_1 exp/tri2b/tree exp/tri2b/final.mdl
fstrmepslocal
fstminimizeencoded
fsttablecompose exp/tri2b/graph_word/Ha.fst data/graph/lang/tmp/CLG_3_1.fst
fstrmsymbols exp/tri2b/graph_word/disambig_tid.int
fstdeterminizestar --use-log=true
bash: line 1: 770 Killed ( gmm-latgen-faster --max-active=7000 --beam=13.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/mono/graph_word/words.txt exp/mono/final.mdl exp/mono/graph_word/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/mfcc/test/split8/6/utt2spk scp:data/mfcc/test/split8/6/cmvn.scp scp:data/mfcc/test/split8/6/feats.scp ark:- | add-deltas ark:- ark:- |" "ark:|gzip -c > exp/mono/decode_test_word/lat.6.gz" ) 2>> exp/mono/decode_test_word/log/decode.6.log >> exp/mono/decode_test_word/log/decode.6.log
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstdeterminizestar[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstdeterminizestar() [0x626f94]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmsymbols[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmsymbols() [0x54d84a]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmepslocal[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmepslocal() [0x573986]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstminimizeencoded[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstminimizeencoded() [0x5c3afe]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
steps/diagnostic/analyze_alignments.sh --cmd run.pl data/lang exp/tri2b_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri2b_ali/log/analyze_alignments.log
steps/align_si.sh: done aligning data.
steps/train_sat.sh --cmd run.pl 2500 15000 data/mfcc/train data/lang exp/tri2b_ali 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
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[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 109 with no stats; corresponding phone list: 110
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 121 with no stats; corresponding phone list: 122
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 163 with no stats; corresponding phone list: 164
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 175 with no stats; corresponding phone list: 176
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 177 with no stats; corresponding phone list: 178
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 203 with no stats; corresponding phone list: 204
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 208 with no stats; corresponding phone list: 209
This is a bad warning.
steps/train_sat.sh: Converting alignments from exp/tri2b_ali 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 data/lang exp/tri3b
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3b/log/analyze_alignments.log
8 warnings in exp/tri3b/log/questions.log
211 warnings in exp/tri3b/log/align.*.*.log
272 warnings in exp/tri3b/log/update.*.log
16 warnings in exp/tri3b/log/fmllr.*.*.log
127 warnings in exp/tri3b/log/acc.*.*.log
1 warnings in exp/tri3b/log/build_tree.log
9 warnings in exp/tri3b/log/init_model.log
1 warnings in exp/tri3b/log/compile_questions.log
8 warnings in exp/tri3b/log/est_alimdl.log
steps/train_sat.sh: Likelihood evolution:
-49.8191 -49.6232 -49.5207 -49.3232 -48.7195 -48.1826 -47.8333 -47.6169 -47.4615 -47.0208 -46.8384 -46.647 -46.5195 -46.4132 -46.3139 -46.2273 -46.1518 -46.0825 -46.0129 -45.8584 -45.7677 -45.7128 -45.662 -45.615 -45.5706 -45.5267 -45.4834 -45.4412 -45.399 -45.3094 -45.2536 -45.2305 -45.2164 -45.2068
exp/tri3b: nj=8 align prob=-48.02 over 25.48h [retry=0.5%, fail=0.0%] states=2074 gauss=15024 fmllr-impr=2.42 over 18.98h tree-impr=6.30
steps/train_sat.sh: done training SAT system in exp/tri3b
steps/align_fmllr.sh --nj 8 --cmd run.pl data/mfcc/train data/lang exp/tri3b exp/tri3b_ali
steps/align_fmllr.sh: feature type is lda
steps/align_fmllr.sh: compiling training graphs
tree-info exp/tri3b/tree
tree-info exp/tri3b/tree
make-h-transducer --disambig-syms-out=exp/tri3b/graph_word/disambig_tid.int --transition-scale=1.0 data/graph/lang/tmp/ilabels_3_1 exp/tri3b/tree exp/tri3b/final.mdl
fstminimizeencoded
fstrmepslocal
fstdeterminizestar --use-log=true
fstrmsymbols exp/tri3b/graph_word/disambig_tid.int
fsttablecompose exp/tri3b/graph_word/Ha.fst data/graph/lang/tmp/CLG_3_1.fst
steps/align_fmllr.sh: aligning data in data/mfcc/train using exp/tri3b/final.alimdl and speaker-independent features.
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstdeterminizestar[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstdeterminizestar() [0x626f94]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmsymbols[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmsymbols() [0x54d84a]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmepslocal[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmepslocal() [0x573986]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstminimizeencoded[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstminimizeencoded() [0x5c3afe]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
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 data/lang exp/tri3b_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3b_ali/log/analyze_alignments.log
54 warnings in exp/tri3b_ali/log/align_pass2.*.log
3 warnings in exp/tri3b_ali/log/fmllr.*.log
31 warnings in exp/tri3b_ali/log/align_pass1.*.log
steps/train_quick.sh --cmd run.pl 4200 40000 data/mfcc/train data/lang exp/tri3b_ali exp/tri4b
steps/train_quick.sh: feature type is lda
steps/train_quick.sh: using transforms from exp/tri3b_ali
steps/train_quick.sh: accumulating tree stats
steps/train_quick.sh: Getting questions for tree clustering.
steps/train_quick.sh: Building the tree
steps/train_quick.sh: Initializing the model
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 109 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 121 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 163 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 175 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 176 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 177 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 203 of new tree has no stats.
WARNING (gmm-init-model[5.1.4-7d53]:InitAmGmmFromOld():gmm-init-model.cc:147) Leaf 208 of new tree has no stats.
steps/train_quick.sh: This is a bad warning.
steps/train_quick.sh: mixing up old model.
steps/train_quick.sh: converting old alignments
steps/train_quick.sh: compiling training graphs
steps/train_quick.sh: pass 1
steps/train_quick.sh: pass 2
steps/train_quick.sh: pass 3
steps/train_quick.sh: pass 4
steps/train_quick.sh: pass 5
steps/train_quick.sh: pass 6
steps/train_quick.sh: pass 7
steps/train_quick.sh: pass 8
steps/train_quick.sh: pass 9
steps/train_quick.sh: pass 10
steps/train_quick.sh: aligning data
steps/train_quick.sh: pass 11
steps/train_quick.sh: pass 12
steps/train_quick.sh: pass 13
steps/train_quick.sh: pass 14
steps/train_quick.sh: pass 15
steps/train_quick.sh: aligning data
steps/train_quick.sh: pass 16
steps/train_quick.sh: pass 17
steps/train_quick.sh: pass 18
steps/train_quick.sh: pass 19
steps/train_quick.sh: estimating alignment model
Done
steps/align_fmllr.sh --nj 8 --cmd run.pl data/mfcc/train data/lang exp/tri4b exp/tri4b_ali
steps/align_fmllr.sh: feature type is lda
steps/align_fmllr.sh: compiling training graphs
tree-info exp/tri4b/tree
tree-info exp/tri4b/tree
make-h-transducer --disambig-syms-out=exp/tri4b/graph_word/disambig_tid.int --transition-scale=1.0 data/graph/lang/tmp/ilabels_3_1 exp/tri4b/tree exp/tri4b/final.mdl
fstminimizeencoded
fstrmepslocal
fstdeterminizestar --use-log=true
fstrmsymbols exp/tri4b/graph_word/disambig_tid.int
fsttablecompose exp/tri4b/graph_word/Ha.fst data/graph/lang/tmp/CLG_3_1.fst
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstdeterminizestar[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstdeterminizestar() [0x626f94]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmsymbols[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmsymbols() [0x54d84a]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstrmepslocal[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstrmepslocal() [0x573986]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
steps/align_fmllr.sh: aligning data in data/mfcc/train using exp/tri4b/final.alimdl and speaker-independent features.
ERROR: FstHeader::Read: Bad FST header: -
ERROR (fstminimizeencoded[5.1.4-7d53]:ReadFstKaldi():kaldi-fst-io.cc:35) Reading FST: error reading FST header from standard input
[ Stack-Trace: ]
fstminimizeencoded() [0x5c3afe]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
fst::ReadFstKaldi(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)
main
__libc_start_main
_start
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 data/lang exp/tri4b_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri4b_ali/log/analyze_alignments.log
40 warnings in exp/tri4b_ali/log/align_pass2.*.log
3 warnings in exp/tri4b_ali/log/fmllr.*.log
30 warnings in exp/tri4b_ali/log/align_pass1.*.log
steps/align_fmllr.sh --nj 8 --cmd run.pl data/mfcc/dev data/lang exp/tri4b exp/tri4b_ali_cv
steps/align_fmllr.sh: feature type is lda
steps/align_fmllr.sh: compiling training graphs
steps/align_fmllr.sh: aligning data in data/mfcc/dev using exp/tri4b/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 data/lang exp/tri4b_ali_cv
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri4b_ali_cv/log/analyze_alignments.log
4 warnings in exp/tri4b_ali_cv/log/align_pass2.*.log
4 warnings in exp/tri4b_ali_cv/log/align_pass1.*.log
DNN training: stage 0: feature generation
producing fbank for train
steps/make_fbank.sh --nj 8 --cmd run.pl data/fbank/train exp/make_fbank/train fbank/train
utils/validate_data_dir.sh: Successfully validated data-directory data/fbank/train
steps/make_fbank.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating filterbank features for train
steps/compute_cmvn_stats.sh data/fbank/train exp/fbank_cmvn/train fbank/train
Succeeded creating CMVN stats for train
producing fbank for dev
steps/make_fbank.sh --nj 8 --cmd run.pl data/fbank/dev exp/make_fbank/dev fbank/dev
utils/validate_data_dir.sh: Successfully validated data-directory data/fbank/dev
steps/make_fbank.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating filterbank features for dev
steps/compute_cmvn_stats.sh data/fbank/dev exp/fbank_cmvn/dev fbank/dev
Succeeded creating CMVN stats for dev
producing fbank for test
steps/make_fbank.sh --nj 8 --cmd run.pl data/fbank/test exp/make_fbank/test fbank/test
utils/validate_data_dir.sh: Successfully validated data-directory data/fbank/test
steps/make_fbank.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating filterbank features for test
steps/compute_cmvn_stats.sh data/fbank/test exp/fbank_cmvn/test fbank/test
Succeeded creating CMVN stats for test
producing test_fbank_phone
local/nnet/run_dnn.sh: line 45: exp/tri4b_dnn/log/train_nnet.log: No such file or directory
转载于:https://my.oschina.net/innovation/blog/863347
3190
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
