aishell第四次训练数据

开始时间:2018年10月22日 8:42 周一
结束时间:2018年10月22日 20:29 周一
===========
local/download_and_untar.sh: data part data_aishell was already successfully extracted, nothing to do.
local/download_and_untar.sh: data part resource_aishell was already successfully extracted, nothing to do.


1 Lexicon Prerain tri1 [first tlparation


local/aishell_prepare_dict.sh: AISHELL dict preparation succeeded
Preparing data/local/train transcriptions
Preparing data/local/dev transcriptions
Preparing data/local/test transcriptions
local/aishell_data_prep.sh: AISHELL data preparation succeeded
utils/prepare_lang.sh --position-dependent-phones false data/local/dict <SPOKEN_NOISE> data/local/lang 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 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 data/local/dict/extra_questions.txt ...
--> reading data/local/dict/extra_questions.txt
--> text seems to be UTF-8 or ASCII, checking whitespaces
--> text contains only allowed whitespaces
--> data/local/dict/extra_questions.txt is OK
--> SUCCESS [validating dictionary directory data/local/dict]

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 ...
--> 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 ...
--> summation property is OK

Checking data/lang/phones/context_indep.{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/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
--> 216 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
--> 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} ...
--> 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
--> 105 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
--> 217 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
--> 217 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
--> 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} ...
--> 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]


2 LM training


Not creating raw N-gram counts ngrams.gz and heldout_ngrams.gz since they already exist in data/local/lm/3gram-mincount
(remove them if you want them regenerated)
Not doing optimization of discounting parameters since
file data/local/lm/3gram-mincount/config.6 already exists
Final config is:
D=0.6 tau=0.527830672157611 phi=2
D=0.706938285164495 tau=0.664727230661135 phi=2.7
D=0 tau=1.09671484103859 phi=1.85025636116095
Not creating discounted N-grams file data/local/lm/3gram-mincount/ngrams_disc.gz since it already exists
Computing final perplexity
Building ARPA LM (perplexity computation is in background)
interpolate_ngrams: 137074 words in wordslist
interpolate_ngrams: 137074 words in wordslist
Perplexity over 99496.000000 words is 567.320537
Perplexity over 99496.000000 words (excluding 0.000000 OOVs) is 567.320537
567.320537
Done training LM of type 3gram-mincount
Converting 'data/local/lm/3gram-mincount/lm_unpruned.gz' to FST
arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test/words.txt - data/lang_test/G.fst
LOG (arpa2fst[5.4]:Read():arpa-file-parser.cc:94) Reading \data\ section.
LOG (arpa2fst[5.4]:Read():arpa-file-parser.cc:149) Reading \1-grams: section.
LOG (arpa2fst[5.4]:Read():arpa-file-parser.cc:149) Reading \2-grams: section.
LOG (arpa2fst[5.4]:Read():arpa-file-parser.cc:149) Reading \3-grams: section.
LOG (arpa2fst[5.4]:RemoveRedundantStates():arpa-lm-compiler.cc:359) Reduced num-states from 561655 to 102646
fstisstochastic data/lang_test/G.fst
8.84583e-06 -0.56498
Succeeded in formatting LM: 'data/local/lm/3gram-mincount/lm_unpruned.gz'


3 make MFCC


steps/make_mfcc_pitch.sh --cmd run.pl --nj 10 data/train exp/make_mfcc/train mfcc
steps/make_mfcc_pitch.sh: moving data/train/feats.scp to data/train/.backup
utils/validate_data_dir.sh: Successfully validated data-directory data/train
steps/make_mfcc_pitch.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating MFCC & Pitch features for train
steps/compute_cmvn_stats.sh data/train exp/make_mfcc/train mfcc
Succeeded creating CMVN stats for train
fix_data_dir.sh: kept all 120098 utterances.
fix_data_dir.sh: old files are kept in data/train/.backup
steps/make_mfcc_pitch.sh --cmd run.pl --nj 10 data/dev exp/make_mfcc/dev mfcc
steps/make_mfcc_pitch.sh: moving data/dev/feats.scp to data/dev/.backup
utils/validate_data_dir.sh: Successfully validated data-directory data/dev
steps/make_mfcc_pitch.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating MFCC & Pitch features for dev
steps/compute_cmvn_stats.sh data/dev exp/make_mfcc/dev mfcc
Succeeded creating CMVN stats for dev
fix_data_dir.sh: kept all 14326 utterances.
fix_data_dir.sh: old files are kept in data/dev/.backup
steps/make_mfcc_pitch.sh --cmd run.pl --nj 10 data/test exp/make_mfcc/test mfcc
steps/make_mfcc_pitch.sh: moving data/test/feats.scp to data/test/.backup
utils/validate_data_dir.sh: Successfully validated data-directory data/test
steps/make_mfcc_pitch.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
Succeeded creating MFCC & Pitch features for test
steps/compute_cmvn_stats.sh data/test exp/make_mfcc/test mfcc
Succeeded creating CMVN stats for test
fix_data_dir.sh: kept all 7176 utterances.
fix_data_dir.sh: old files are kept in data/test/.backup
steps/train_mono.sh --cmd run.pl --nj 10 data/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
56557 warnings in exp/mono/log/align...log
2069 warnings in exp/mono/log/acc...log
827 warnings in exp/mono/log/update.*.log
exp/mono: nj=10 align prob=-82.87 over 150.12h [retry=1.6%, fail=0.0%] states=653 gauss=985
steps/train_mono.sh: Done training monophone system in exp/mono


4 Monophone decoding


tree-info exp/mono/tree
tree-info exp/mono/tree
fstpushspecial
fsttablecompose data/lang_test/L_disambig.fst data/lang_test/G.fst
fstminimizeencoded
fstdeterminizestar --use-log=true
fstisstochastic data/lang_test/tmp/LG.fst
-0.0663446 -0.0666824
[info]: LG not stochastic.
fstcomposecontext --context-size=1 --central-position=0 --read-disambig-syms=data/lang_test/phones/disambig.int --write-disambig-syms=data/lang_test/tmp/disambig_ilabels_1_0.int data/lang_test/tmp/ilabels_1_0.25902
fstisstochastic data/lang_test/tmp/CLG_1_0.fst
-0.0663446 -0.0666824
[info]: CLG not stochastic.
make-h-transducer --disambig-syms-out=exp/mono/graph/disambig_tid.int --transition-scale=1.0 data/lang_test/tmp/ilabels_1_0 exp/mono/tree exp/mono/final.mdl
fstrmepslocal
fsttablecompose exp/mono/graph/Ha.fst data/lang_test/tmp/CLG_1_0.fst
fstminimizeencoded
fstrmsymbols exp/mono/graph/disambig_tid.int
fstdeterminizestar --use-log=true
fstisstochastic exp/mono/graph/HCLGa.fst
0.000157882 -0.132761
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/mono/final.mdl
steps/decode.sh --cmd run.pl --mem 16G --config conf/decode.config --nj 10 exp/mono/graph data/dev exp/mono/decode_dev
decode.sh: feature type is delta
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/mono/graph exp/mono/decode_dev
steps/diagnostic/analyze_lats.sh: see stats in exp/mono/decode_dev/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,11,91) and mean=34.5
steps/diagnostic/analyze_lats.sh: see stats in exp/mono/decode_dev/log/analyze_lattice_depth_stats.log

  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/dev exp/mono/graph exp/mono/decode_dev
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/dev exp/mono/graph exp/mono/decode_dev
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/dev exp/mono/graph exp/mono/decode_dev
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/dev exp/mono/graph exp/mono/decode_dev
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done
    steps/decode.sh --cmd run.pl --mem 16G --config conf/decode.config --nj 10 exp/mono/graph data/test exp/mono/decode_test
    decode.sh: feature type is delta
    steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/mono/graph exp/mono/decode_test
    steps/diagnostic/analyze_lats.sh: see stats in exp/mono/decode_test/log/analyze_alignments.log
    Overall, lattice depth (10,50,90-percentile)=(1,14,105) and mean=40.1
    steps/diagnostic/analyze_lats.sh: see stats in exp/mono/decode_test/log/analyze_lattice_depth_stats.log
  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/test exp/mono/graph exp/mono/decode_test
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/test exp/mono/graph exp/mono/decode_test
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/test exp/mono/graph exp/mono/decode_test
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/test exp/mono/graph exp/mono/decode_test
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done

5 Get alignments from monophone system.


steps/align_si.sh --cmd run.pl --nj 10 data/train data/lang exp/mono exp/mono_ali
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
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 --cmd run.pl 2500 20000 data/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[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 83 with no stats; corresponding phone list: 84
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 174 with no stats; corresponding phone list: 175
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 207 with no stats; corresponding phone list: 208
** 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
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 data/lang exp/tri1
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri1/log/analyze_alignments.log
1 warnings in exp/tri1/log/compile_questions.log
1487 warnings in exp/tri1/log/acc...log
4843 warnings in exp/tri1/log/align...log
1 warnings in exp/tri1/log/build_tree.log
177 warnings in exp/tri1/log/update.*.log
9 warnings in exp/tri1/log/init_model.log
3 warnings in exp/tri1/log/questions.log
exp/tri1: nj=10 align prob=-79.54 over 150.16h [retry=0.8%, fail=0.0%] states=2128 gauss=20053 tree-impr=4.34
steps/train_deltas.sh: Done training system with delta+delta-delta features in exp/tri1


6 decode tri1


tree-info exp/tri1/tree
tree-info exp/tri1/tree
fstcomposecontext --context-size=3 --central-position=1 --read-disambig-syms=data/lang_test/phones/disambig.int --write-disambig-syms=data/lang_test/tmp/disambig_ilabels_3_1.int data/lang_test/tmp/ilabels_3_1.9979
fstisstochastic data/lang_test/tmp/CLG_3_1.fst
0 -0.0666824
[info]: CLG not stochastic.
make-h-transducer --disambig-syms-out=exp/tri1/graph/disambig_tid.int --transition-scale=1.0 data/lang_test/tmp/ilabels_3_1 exp/tri1/tree exp/tri1/final.mdl
fstrmepslocal
fstminimizeencoded
fsttablecompose exp/tri1/graph/Ha.fst data/lang_test/tmp/CLG_3_1.fst
fstrmsymbols exp/tri1/graph/disambig_tid.int
fstdeterminizestar --use-log=true
fstisstochastic exp/tri1/graph/HCLGa.fst
0.000487079 -0.178947
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/tri1/final.mdl
steps/decode.sh --cmd run.pl --mem 16G --config conf/decode.config --nj 10 exp/tri1/graph data/dev exp/tri1/decode_dev
decode.sh: feature type is delta
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/tri1/graph exp/tri1/decode_dev
steps/diagnostic/analyze_lats.sh: see stats in exp/tri1/decode_dev/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,4,30) and mean=11.8
steps/diagnostic/analyze_lats.sh: see stats in exp/tri1/decode_dev/log/analyze_lattice_depth_stats.log

  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/dev exp/tri1/graph exp/tri1/decode_dev
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/dev exp/tri1/graph exp/tri1/decode_dev
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/dev exp/tri1/graph exp/tri1/decode_dev
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/dev exp/tri1/graph exp/tri1/decode_dev
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done
    steps/decode.sh --cmd run.pl --mem 16G --config conf/decode.config --nj 10 exp/tri1/graph data/test exp/tri1/decode_test
    decode.sh: feature type is delta
    steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/tri1/graph exp/tri1/decode_test
    steps/diagnostic/analyze_lats.sh: see stats in exp/tri1/decode_test/log/analyze_alignments.log
    Overall, lattice depth (10,50,90-percentile)=(1,5,39) and mean=15.4
    steps/diagnostic/analyze_lats.sh: see stats in exp/tri1/decode_test/log/analyze_lattice_depth_stats.log
  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/test exp/tri1/graph exp/tri1/decode_test
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/test exp/tri1/graph exp/tri1/decode_test
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/test exp/tri1/graph exp/tri1/decode_test
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/test exp/tri1/graph exp/tri1/decode_test
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done

7 align tri1


steps/align_si.sh --cmd run.pl --nj 10 data/train data/lang exp/tri1 exp/tri1_ali
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
steps/diagnostic/analyze_alignments.sh --cmd run.pl data/lang exp/tri1_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri1_ali/log/analyze_alignments.log
steps/align_si.sh: done aligning data.


8 train tri2 [delta+delta-deltas]


steps/train_deltas.sh --cmd run.pl 2500 20000 data/train data/lang exp/tri1_ali exp/tri2
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[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 83 with no stats; corresponding phone list: 84
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 104 with no stats; corresponding phone list: 105
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 174 with no stats; corresponding phone list: 175
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 207 with no stats; corresponding phone list: 208
** 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/tri1_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
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 data/lang exp/tri2
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri2/log/analyze_alignments.log
1 warnings in exp/tri2/log/compile_questions.log
204 warnings in exp/tri2/log/update..log
5 warnings in exp/tri2/log/questions.log
10 warnings in exp/tri2/log/init_model.log
1 warnings in exp/tri2/log/build_tree.log
2990 warnings in exp/tri2/log/align.
..log
775 warnings in exp/tri2/log/acc.
.*.log
exp/tri2: nj=10 align prob=-79.48 over 150.17h [retry=0.5%, fail=0.0%] states=2152 gauss=20039 tree-impr=4.57
steps/train_deltas.sh: Done training system with delta+delta-delta features in exp/tri2


9 decode tri2


tree-info exp/tri2/tree
tree-info exp/tri2/tree
make-h-transducer --disambig-syms-out=exp/tri2/graph/disambig_tid.int --transition-scale=1.0 data/lang_test/tmp/ilabels_3_1 exp/tri2/tree exp/tri2/final.mdl
fstrmepslocal
fstminimizeencoded
fsttablecompose exp/tri2/graph/Ha.fst data/lang_test/tmp/CLG_3_1.fst
fstrmsymbols exp/tri2/graph/disambig_tid.int
fstdeterminizestar --use-log=true
fstisstochastic exp/tri2/graph/HCLGa.fst
0.000487832 -0.178947
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/tri2/final.mdl
steps/decode.sh --cmd run.pl --mem 16G --config conf/decode.config --nj 10 exp/tri2/graph data/dev exp/tri2/decode_dev
decode.sh: feature type is delta
run.pl: 1 / 10 failed, log is in exp/tri2/decode_dev/log/decode.*.log
steps/decode.sh --cmd run.pl --mem 16G --config conf/decode.config --nj 10 exp/tri2/graph data/test exp/tri2/decode_test
decode.sh: feature type is delta
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/tri2/graph exp/tri2/decode_test
steps/diagnostic/analyze_lats.sh: see stats in exp/tri2/decode_test/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,4,38) and mean=15.1
steps/diagnostic/analyze_lats.sh: see stats in exp/tri2/decode_test/log/analyze_lattice_depth_stats.log

  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/test exp/tri2/graph exp/tri2/decode_test
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/test exp/tri2/graph exp/tri2/decode_test
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/test exp/tri2/graph exp/tri2/decode_test
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/test exp/tri2/graph exp/tri2/decode_test
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done

10 train and decode tri2b [LDA+MLLT]


steps/align_si.sh --cmd run.pl --nj 10 data/train data/lang exp/tri2 exp/tri2_ali
steps/align_si.sh: feature type is delta
steps/align_si.sh: aligning data in data/train using model from exp/tri2, putting alignments in exp/tri2_ali
steps/diagnostic/analyze_alignments.sh --cmd run.pl data/lang exp/tri2_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri2_ali/log/analyze_alignments.log
steps/align_si.sh: done aligning data.


11 Train tri3a, which is LDA+MLLT


steps/train_lda_mllt.sh --cmd run.pl 2500 20000 data/train data/lang exp/tri2_ali exp/tri3a
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[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 104 with no stats; corresponding phone list: 105
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 174 with no stats; corresponding phone list: 175
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 207 with no stats; corresponding phone list: 208
This is a bad warning.
steps/train_lda_mllt.sh: Converting alignments from exp/tri2_ali 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 data/lang exp/tri3a
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3a/log/analyze_alignments.log
1426 warnings in exp/tri3a/log/align...log
1 warnings in exp/tri3a/log/build_tree.log
4 warnings in exp/tri3a/log/questions.log
204 warnings in exp/tri3a/log/update..log
11 warnings in exp/tri3a/log/lda_acc.
.log
10 warnings in exp/tri3a/log/init_model.log
359 warnings in exp/tri3a/log/acc...log
1 warnings in exp/tri3a/log/compile_questions.log
exp/tri3a: nj=10 align prob=-48.79 over 150.18h [retry=0.3%, fail=0.0%] states=2096 gauss=20042 tree-impr=4.77 lda-sum=24.25 mllt:impr,logdet=0.93,1.39
steps/train_lda_mllt.sh: Done training system with LDA+MLLT features in exp/tri3a
tree-info exp/tri3a/tree
tree-info exp/tri3a/tree
make-h-transducer --disambig-syms-out=exp/tri3a/graph/disambig_tid.int --transition-scale=1.0 data/lang_test/tmp/ilabels_3_1 exp/tri3a/tree exp/tri3a/final.mdl
fsttablecompose exp/tri3a/graph/Ha.fst data/lang_test/tmp/CLG_3_1.fst
fstdeterminizestar --use-log=true
fstrmsymbols exp/tri3a/graph/disambig_tid.int
fstrmepslocal
fstminimizeencoded
fstisstochastic exp/tri3a/graph/HCLGa.fst
0.000487099 -0.178947
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/tri3a/final.mdl
steps/decode.sh --cmd run.pl --mem 16G --nj 10 --config conf/decode.config exp/tri3a/graph data/dev exp/tri3a/decode_dev
decode.sh: feature type is lda
bash: line 1: 10636 Aborted (core dumped) ( gmm-latgen-faster --max-active=7000 --beam=11.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/tri3a/graph/words.txt exp/tri3a/final.mdl exp/tri3a/graph/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/dev/split10/9/utt2spk scp:data/dev/split10/9/cmvn.scp scp:data/dev/split10/9/feats.scp ark:- | splice-feats ark:- ark:- | transform-feats exp/tri3a/final.mat ark:- ark:- |" "ark:|gzip -c > exp/tri3a/decode_dev/lat.9.gz" ) 2>> exp/tri3a/decode_dev/log/decode.9.log >> exp/tri3a/decode_dev/log/decode.9.log
run.pl: 1 / 10 failed, log is in exp/tri3a/decode_dev/log/decode.*.log
steps/decode.sh --cmd run.pl --mem 16G --nj 10 --config conf/decode.config exp/tri3a/graph data/test exp/tri3a/decode_test
decode.sh: feature type is lda
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/tri3a/graph exp/tri3a/decode_test
steps/diagnostic/analyze_lats.sh: see stats in exp/tri3a/decode_test/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,4,29) and mean=11.6
steps/diagnostic/analyze_lats.sh: see stats in exp/tri3a/decode_test/log/analyze_lattice_depth_stats.log

  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/test exp/tri3a/graph exp/tri3a/decode_test
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/test exp/tri3a/graph exp/tri3a/decode_test
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/test exp/tri3a/graph exp/tri3a/decode_test
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/test exp/tri3a/graph exp/tri3a/decode_test
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done

12 do the alignment with fMLLR


steps/align_fmllr.sh --cmd run.pl --nj 10 data/train data/lang exp/tri3a exp/tri3a_ali
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/tri3a/final.mdl 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/tri3a_ali
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri3a_ali/log/analyze_alignments.log
7 warnings in exp/tri3a_ali/log/fmllr..log
271 warnings in exp/tri3a_ali/log/align_pass1.
.log
270 warnings in exp/tri3a_ali/log/align_pass2..log
steps/train_sat.sh --cmd run.pl 2500 20000 data/train data/lang exp/tri3a_ali exp/tri4a
steps/train_sat.sh: feature type is lda
steps/train_sat.sh: Using transforms from exp/tri3a_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[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 83 with no stats; corresponding phone list: 84
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 104 with no stats; corresponding phone list: 105
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 174 with no stats; corresponding phone list: 175
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 207 with no stats; corresponding phone list: 208
This is a bad warning.
steps/train_sat.sh: Converting alignments from exp/tri3a_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/tri4a
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri4a/log/analyze_alignments.log
1754 warnings in exp/tri4a/log/align.
..log
1 warnings in exp/tri4a/log/build_tree.log
5 warnings in exp/tri4a/log/questions.log
209 warnings in exp/tri4a/log/update.
.log
7 warnings in exp/tri4a/log/est_alimdl.log
12 warnings in exp/tri4a/log/init_model.log
57 warnings in exp/tri4a/log/fmllr...log
1 warnings in exp/tri4a/log/compile_questions.log
823 warnings in exp/tri4a/log/acc...log
steps/train_sat.sh: Likelihood evolution:
-49.2444 -49.056 -48.9352 -48.8032 -48.3523 -47.9253 -47.5925 -47.3713 -47.2036 -46.814 -46.6659 -46.4638 -46.3541 -46.2728 -46.203 -46.1376 -46.0731 -46.0071 -45.942 -45.8044 -45.7327 -45.6907 -45.6537 -45.6194 -45.5871 -45.5564 -45.5268 -45.4982 -45.4708 -45.3995 -45.3598 -45.3394 -45.3261 -45.3169
exp/tri4a: nj=10 align prob=-48.27 over 150.16h [retry=0.3%, fail=0.0%] states=2216 gauss=20026 fmllr-impr=0.63 over 115.02h tree-impr=6.64
steps/train_sat.sh: done training SAT system in exp/tri4a
tree-info exp/tri4a/tree
tree-info exp/tri4a/tree
make-h-transducer --disambig-syms-out=exp/tri4a/graph/disambig_tid.int --transition-scale=1.0 data/lang_test/tmp/ilabels_3_1 exp/tri4a/tree exp/tri4a/final.mdl
fstrmepslocal
fsttablecompose exp/tri4a/graph/Ha.fst data/lang_test/tmp/CLG_3_1.fst
fstminimizeencoded
fstrmsymbols exp/tri4a/graph/disambig_tid.int
fstdeterminizestar --use-log=true
fstisstochastic exp/tri4a/graph/HCLGa.fst
0.000487099 -0.178947
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/tri4a/final.mdl
steps/decode_fmllr.sh --cmd run.pl --mem 16G --nj 10 --config conf/decode.config exp/tri4a/graph data/dev exp/tri4a/decode_dev
steps/decode.sh --scoring-opts --num-threads 1 --skip-scoring false --acwt 0.083333 --nj 10 --cmd run.pl --mem 16G --beam 8.0 --model exp/tri4a/final.alimdl --max-active 2000 exp/tri4a/graph data/dev exp/tri4a/decode_dev.si
decode.sh: feature type is lda
bash: line 1: 26293 Aborted (core dumped) ( gmm-latgen-faster --max-active=2000 --beam=8.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/tri4a/graph/words.txt exp/tri4a/final.alimdl exp/tri4a/graph/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/dev/split10/9/utt2spk scp:data/dev/split10/9/cmvn.scp scp:data/dev/split10/9/feats.scp ark:- | splice-feats ark:- ark:- | transform-feats exp/tri4a/final.mat ark:- ark:- |" "ark:|gzip -c > exp/tri4a/decode_dev.si/lat.9.gz" ) 2>> exp/tri4a/decode_dev.si/log/decode.9.log >> exp/tri4a/decode_dev.si/log/decode.9.log
run.pl: 1 / 10 failed, log is in exp/tri4a/decode_dev.si/log/decode.*.log
steps/decode_fmllr.sh --cmd run.pl --mem 16G --nj 10 --config conf/decode.config exp/tri4a/graph data/test exp/tri4a/decode_test
steps/decode.sh --scoring-opts --num-threads 1 --skip-scoring false --acwt 0.083333 --nj 10 --cmd run.pl --mem 16G --beam 8.0 --model exp/tri4a/final.alimdl --max-active 2000 exp/tri4a/graph data/test exp/tri4a/decode_test.si
decode.sh: feature type is lda
steps/diagnostic/analyze_lats.sh --cmd run.pl --mem 16G exp/tri4a/graph exp/tri4a/decode_test.si
steps/diagnostic/analyze_lats.sh: see stats in exp/tri4a/decode_test.si/log/analyze_alignments.log
Overall, lattice depth (10,50,90-percentile)=(1,3,18) and mean=7.5
steps/diagnostic/analyze_lats.sh: see stats in exp/tri4a/decode_test.si/log/analyze_lattice_depth_stats.log

  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/test exp/tri4a/graph exp/tri4a/decode_test.si
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/test exp/tri4a/graph exp/tri4a/decode_test.si
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/test exp/tri4a/graph exp/tri4a/decode_test.si
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/test exp/tri4a/graph exp/tri4a/decode_test.si
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done
    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 16G exp/tri4a/graph exp/tri4a/decode_test
    steps/diagnostic/analyze_lats.sh: see stats in exp/tri4a/decode_test/log/analyze_alignments.log
    Overall, lattice depth (10,50,90-percentile)=(1,3,19) and mean=7.8
    steps/diagnostic/analyze_lats.sh: see stats in exp/tri4a/decode_test/log/analyze_lattice_depth_stats.log
  • steps/score_kaldi.sh --cmd 'run.pl --mem 16G' data/test exp/tri4a/graph exp/tri4a/decode_test
    steps/score_kaldi.sh --cmd run.pl --mem 16G data/test exp/tri4a/graph exp/tri4a/decode_test
    steps/score_kaldi.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • steps/scoring/score_kaldi_cer.sh --stage 2 --cmd 'run.pl --mem 16G' data/test exp/tri4a/graph exp/tri4a/decode_test
    steps/scoring/score_kaldi_cer.sh --stage 2 --cmd run.pl --mem 16G data/test exp/tri4a/graph exp/tri4a/decode_test
    steps/scoring/score_kaldi_cer.sh: scoring with word insertion penalty=0.0,0.5,1.0
  • echo 'local/score.sh: Done'
    local/score.sh: Done
    steps/align_fmllr.sh --cmd run.pl --nj 10 data/train data/lang exp/tri4a exp/tri4a_ali
    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/tri4a/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/tri4a_ali
    steps/diagnostic/analyze_alignments.sh: see stats in exp/tri4a_ali/log/analyze_alignments.log
    224 warnings in exp/tri4a_ali/log/align_pass1..log
    346 warnings in exp/tri4a_ali/log/align_pass2.
    .log
    2 warnings in exp/tri4a_ali/log/fmllr.*.log

13 Building a larger SAT system.


steps/train_sat.sh --cmd run.pl 3500 100000 data/train data/lang exp/tri4a_ali exp/tri5a
steps/train_sat.sh: feature type is lda
steps/train_sat.sh: Using transforms from exp/tri4a_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[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 104 with no stats; corresponding phone list: 105
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 174 with no stats; corresponding phone list: 175
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 176 with no stats; corresponding phone list: 177
WARNING (gmm-init-model[5.4]:InitAmGmm():gmm-init-model.cc:55) Tree has pdf-id 207 with no stats; corresponding phone list: 208
This is a bad warning.
steps/train_sat.sh: Converting alignments from exp/tri4a_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/tri5a
steps/diagnostic/analyze_alignments.sh: see stats in exp/tri5a/log/analyze_alignments.log
12 warnings in exp/tri5a/log/init_model.log
1 warnings in exp/tri5a/log/build_tree.log
8 warnings in exp/tri5a/log/est_alimdl.log
246 warnings in exp/tri5a/log/update..log
299 warnings in exp/tri5a/log/acc.
..log
1 warnings in exp/tri5a/log/compile_questions.log
47 warnings in exp/tri5a/log/fmllr.
..log
777 warnings in exp/tri5a/log/align.
..log
4 warnings in exp/tri5a/log/questions.log
steps/train_sat.sh: Likelihood evolution:
-48.5893 -48.6317 -48.5743 -48.3316 -47.8291 -47.1419 -46.5876 -46.2201 -45.9509 -45.6172 -45.4499 -45.1891 -45.0612 -44.9675 -44.8832 -44.8077 -44.7394 -44.6765 -44.6168 -44.4937 -44.4229 -44.3764 -44.3351 -44.2961 -44.2595 -44.2249 -44.1917 -44.1596 -44.1283 -44.0622 -44.0185 -43.9937 -43.9764 -43.9643
exp/tri5a: nj=10 align prob=-47.08 over 150.19h [retry=0.1%, fail=0.0%] states=2984 gauss=100122 fmllr-impr=0.26 over 116.09h tree-impr=7.20
steps/train_sat.sh: done training SAT system in exp/tri5a
tree-info exp/tri5a/tree
tree-info exp/tri5a/tree
make-h-transducer --disambig-syms-out=exp/tri5a/graph/disambig_tid.int --transition-scale=1.0 data/lang_test/tmp/ilabels_3_1 exp/tri5a/tree exp/tri5a/final.mdl
fstrmepslocal
fsttablecompose exp/tri5a/graph/Ha.fst data/lang_test/tmp/CLG_3_1.fst
fstminimizeencoded
fstrmsymbols exp/tri5a/graph/disambig_tid.int
fstdeterminizestar --use-log=true
fstisstochastic exp/tri5a/graph/HCLGa.fst
0.00048784 -0.178947
HCLGa is not stochastic
add-self-loops --self-loop-scale=0.1 --reorder=true exp/tri5a/final.mdl
steps/decode_fmllr.sh --cmd run.pl --mem 16G --nj 10 --config conf/decode.config exp/tri5a/graph data/dev exp/tri5a/decode_dev
steps/decode.sh --scoring-opts --num-threads 1 --skip-scoring false --acwt 0.083333 --nj 10 --cmd run.pl --mem 16G --beam 8.0 --model exp/tri5a/final.alimdl --max-active 2000 exp/tri5a/graph data/dev exp/tri5a/decode_dev.si
decode.sh: feature type is lda
bash: line 1: 16183 Aborted (core dumped) ( gmm-latgen-faster --max-active=2000 --beam=8.0 --lattice-beam=6.0 --acoustic-scale=0.083333 --allow-partial=true --word-symbol-table=exp/tri5a/graph/words.txt exp/tri5a/final.alimdl exp/tri5a/graph/HCLG.fst "ark,s,cs:apply-cmvn --utt2spk=ark:data/dev/split10/9/utt2spk scp:data/dev/split10/9/cmvn.scp scp:data/dev/split10/9/feats.scp ark:- | splice-feats ark:- ark:- | transform-feats exp/tri5a/final.mat ark:- ark:- |" "ark:|gzip -c > exp/tri5a/decode_dev.si/lat.9.gz" ) 2>> exp/tri5a/decode_dev.si/log/decode.9.log >> exp/tri5a/decode_dev.si/log/decode.9.log
run.pl: 1 / 10 failed, log is in exp/tri5a/decode_dev.si/log/decode.
.log

©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 202,905评论 5 476
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 85,140评论 2 379
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 149,791评论 0 335
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 54,483评论 1 273
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 63,476评论 5 364
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 48,516评论 1 281
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 37,905评论 3 395
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 36,560评论 0 256
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 40,778评论 1 296
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 35,557评论 2 319
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 37,635评论 1 329
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 33,338评论 4 318
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 38,925评论 3 307
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 29,898评论 0 19
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 31,142评论 1 259
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 42,818评论 2 349
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 42,347评论 2 342

推荐阅读更多精彩内容