精通
英语
和
开源
,
擅长
开发
与
培训
,
胸怀四海
第一信赖
LOG (gmm-boost-silence[5.4.164~6-13ed]:main():gmm-boost-silence.cc:93) Boosted weights for 3 pdfs, by factor of 1
LOG (gmm-boost-silence[5.4.164~6-13ed]:main():gmm-boost-silence.cc:103) Wrote model to -
transform-feats exp/tri4b/final.mat ark:- ark:-
apply-cmvn --utt2spk=ark:data/train_960_30k/split1/1/utt2spk scp:data/train_960_30k/split1/1/cmvn.scp scp:data/train_960_30k/split1/1/feats.scp ark:-
Attempting to read key A01_001, which is not present in utt2spk map or similar map being read from ark:data/train_960_30k/split1/1/utt2spk
[ Stack-Trace: ]
kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
kaldi::RandomAccessTableReaderMapped<kaldi::KaldiObjectHolder<kaldi::Matrix<double> > >::HasKey(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
main
__libc_start_main
_start
拷贝过去主要的uttspk文件,出:
LOG (gmm-boost-silence[5.4.164~6-13ed]:main():gmm-boost-silence.cc:93) Boosted weights for 3 pdfs, by factor of 1
LOG (gmm-boost-silence[5.4.164~6-13ed]:main():gmm-boost-silence.cc:103) Wrote model to -
transform-feats exp/tri4b/final.mat ark:- ark:-
apply-cmvn --utt2spk=ark:data/train_960_30k/split1/1/utt2spk scp:data/train_960_30k/split1/1/cmvn.scp scp:data/train_960_30k/split1/1/feats.scp ark:-
splice-feats --left-context=3 --right-context=3 ark:- ark:-
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_001 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_002 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_003 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_004 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_005 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_006 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_007 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_008 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_009 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_010 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_011 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_012 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_013 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_014 has bad dimension 15x91 versus feat dim 280
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_015 has bad dimension 15x91 versus feat dim 280
LOG (apply-cmvn[5.4.164~6-13ed]:main():apply-cmvn.cc:162) Applied cepstral mean normalization to 16 utterances, errors on 0
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_016 has bad dimension 15x91 versus feat dim 280
LOG (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:161) Applied transform to 0 utterances; 16 had errors.
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_001
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_002
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_003
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_004
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_005
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_006
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_007
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_008
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_009
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_010
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_011
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_012
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_013
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_014
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_015
WARNING (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:103) No features for utterance A01_016
LOG (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:135) Overall log-likelihood per frame is -nan over 0 frames.
LOG (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:137) Retried 0 out of 16 utterances.
LOG (gmm-align-compiled[5.4.164~6-13ed]:main():gmm-align-compiled.cc:139) Done 0, errors on 16
WARNING (gmm-align-compiled[5.4.164~6-13ed]:Close():kaldi-io.cc:515) Pipe apply-cmvn --utt2spk=ark:data/train_960_30k/split1/1/utt2spk scp:data/train_960_30k/split1/1/cmvn.scp scp:data/train_960_30k/split1/1/feats.scp ark:- | splice-feats --left-context=3 --right-context=3 ark:- ark:- | transform-feats exp/tri4b/final.mat ark:- ark:- | had nonzero return status 256
utils/create_split_dir.pl好像是这个命令和thchs30数据不匹配,进行不了后续分析
cannot subset to more utterances than you originally had.
utils/subset_data_dir.sh --first data/train_si284_hires 1 data/train_si84_hires || exit 1
cat: data/train_si84/utt2spk: No such file or directory
从hire目录拷贝过去
Failed to open utt2spk file data/train_si84/utt2spk at utils/split_scp.pl line 85.
steps/align_fmllr.sh --nj 40 --cmd run.pl data/train_si84 data/lang exp/tri4b exp/nnet2_online/tri4b_ali_si84
Refusing to split data because number of speakers 1 is less than the number of output .scp files 40 at utils/split_scp.pl line 114, <I> line 1.
No such file exp/nnet2_online/diag_ubm/final.dubm
steps/align_fmllr.sh: aligning data in data/train_si84 using exp/tri4b/final.alimdl and speaker-independent features.
run.pl: job failed, log is in exp/nnet2_online/tri4b_ali_si84/log/align_pass1.1.log
steps/train_lda_mllt.sh --cmd run.pl --num-iters 13 --realign-iters --splice-opts --left-context=3 --right-context=3 5000 10000 data/train_si84_hires data/lang exp/nnet2_online/tri4b_ali_si84 exp/nnet2_online/tri5b
train_lda_mllt.sh: no such file exp/nnet2_online/tri4b_ali_si84/ali.1.gz
steps/online/nnet2/train_diag_ubm.sh --cmd run.pl --nj 1 --num-frames 400000 data/train_si84_hires 256 exp/nnet2_online/tri5b exp/nnet2_online/diag_ubm
steps/online/nnet2/train_diag_ubm.sh: expecting file conf/online_cmvn.conf to exist
steps/online/nnet2/train_ivector_extractor.sh --cmd run.pl --nj 10 data/train_si284_hires exp/nnet2_online/diag_ubm exp/nnet2_online/extractor
No such file exp/nnet2_online/diag_ubm/final.dubm
# gmm-align-compiled --transition-scale=1.0 --acoustic-scale=0.1 --self-loop-scale=0.1 --beam=10 --retry-beam=40 --careful=false "gmm-boost-silence --boost=1.0 1 exp/tri4b/final.alimdl - |" "ark:gunzip -c exp/nnet2_online/tri4b_ali_si84/fsts.1.gz|" "ark,s,cs:apply-cmvn --utt2spk=ark:data/train_si84/split1/1/utt2spk scp:data/train_si84/split1/1/cmvn.scp scp:data/train_si84/split1/1/feats.scp ark:- | splice-feats --left-context=3 --right-context=3 ark:- ark:- | transform-feats exp/tri4b/final.mat ark:- ark:- |" "ark:|gzip -c >exp/nnet2_online/tri4b_ali_si84/pre_ali.1.gz"
# Started at Fri Oct 9 16:31:04 CST 2020
#
gmm-align-compiled --transition-scale=1.0 --acoustic-scale=0.1 --self-loop-scale=0.1 --beam=10 --retry-beam=40 --careful=false 'gmm-boost-silence --boost=1.0 1 exp/tri4b/final.alimdl - |' 'ark:gunzip -c exp/nnet2_online/tri4b_ali_si84/fsts.1.gz|' 'ark,s,cs:apply-cmvn --utt2spk=ark:data/train_si84/split1/1/utt2spk scp:data/train_si84/split1/1/cmvn.scp scp:data/train_si84/split1/1/feats.scp ark:- | splice-feats --left-context=3 --right-context=3 ark:- ark:- | transform-feats exp/tri4b/final.mat ark:- ark:- |' 'ark:|gzip -c >exp/nnet2_online/tri4b_ali_si84/pre_ali.1.gz'
gmm-boost-silence --boost=1.0 1 exp/tri4b/final.alimdl -
LOG (gmm-boost-silence[5.4.164~6-13ed]:main():gmm-boost-silence.cc:93) Boosted weights for 3 pdfs, by factor of 1
LOG (gmm-boost-silence[5.4.164~6-13ed]:main():gmm-boost-silence.cc:103) Wrote model to -
transform-feats exp/tri4b/final.mat ark:- ark:-
apply-cmvn --utt2spk=ark:data/train_si84/split1/1/utt2spk scp:data/train_si84/split1/1/cmvn.scp scp:data/train_si84/split1/1/feats.scp ark:-
splice-feats --left-context=3 --right-context=3 ark:- ark:-
LOG (apply-cmvn[5.4.164~6-13ed]:main():apply-cmvn.cc:162) Applied cepstral mean normalization to 1 utterances, errors on 0
WARNING (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:110) Transform matrix for utterance A01_001 has bad dimension 15x91 versus feat dim 280
LOG (transform-feats[5.4.164~6-13ed]:main():transform-feats.cc:161) Applied transform to 0 utterances; 1 had errors.