Closed benfoley closed 3 years ago
It's really confusing that 'job failed' but actually training was oK.
b'fstaddselfloops data/lang/phones/wdisambig_phones.int data/lang/phones/wdisambig_words.int \narpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang/words.txt data/local/tmp/lm.arpa data/lang/G.fst \nLOG (arpa2fst[5.3.118~1-6d32a]:Read():arpa-file-parser.cc:94) Reading \\data\\ section.\nLOG (arpa2fst[5.3.118~1-6d32a]:Read():arpa-file-parser.cc:149) Reading \\1-grams: section.\nLOG (arpa2fst[5.3.118~1-6d32a]:RemoveRedundantStates():arpa-lm-compiler.cc:359) Reduced num-states from 1 to 1\nrun.pl: job failed, log is in exp/mono/log/analyze_alignments.log\ntree-info exp/mono/tree \ntree-info exp/mono/tree \nfstminimizeencoded \nfstpushspecial \nfsttablecompose data/lang/L_disambig.fst data/lang/G.fst \nfstdeterminizestar --use-log=true \nfstisstochastic data/lang/tmp/LG.fst \nfstcomposecontext --context-size=1 --central-position=0 --read-disambig-syms=data/lang/phones/disambig.int --write-disambig-syms=data/lang/tmp/disambig_ilabels_1_0.int data/lang/tmp/ilabels_1_0.2748 \nfstisstochastic data/lang/tmp/CLG_1_0.fst \nmake-h-transducer --disambig-syms-out=exp/mono/graph/disambig_tid.int --transition-scale=1.0 data/lang/tmp/ilabels_1_0 exp/mono/tree exp/mono/final.mdl \nfsttablecompose exp/mono/graph/Ha.fst data/lang/tmp/CLG_1_0.fst \nfstrmsymbols exp/mono/graph/disambig_tid.int \nfstrmepslocal \nfstdeterminizestar --use-log=true \nfstminimizeencoded \nfstisstochastic exp/mono/graph/HCLGa.fst \nadd-self-loops --self-loop-scale=0.1 --reorder=true exp/mono/final.mdl \nrun.pl: job failed, log is in exp/mono/decode/log/analyze_alignments.log\nrun.pl: job failed, log is in exp/mono_ali/log/analyze_alignments.log\nrun.pl: job failed, log is in exp/tri1/log/analyze_alignments.log\ntree-info exp/tri1/tree \ntree-info exp/tri1/tree \nfstcomposecontext --context-size=3 --central-position=1 --read-disambig-syms=data/lang/phones/disambig.int --write-disambig-syms=data/lang/tmp/disambig_ilabels_3_1.int data/lang/tmp/ilabels_3_1.4746 \nfstisstochastic data/lang/tmp/CLG_3_1.fst \nmake-h-transducer --disambig-syms-out=exp/tri1/graph/disambig_tid.int --transition-scale=1.0 data/lang/tmp/ilabels_3_1 exp/tri1/tree exp/tri1/final.mdl \nfstrmepslocal \nfsttablecompose exp/tri1/graph/Ha.fst data/lang/tmp/CLG_3_1.fst \nfstdeterminizestar --use-log=true \nfstrmsymbols exp/tri1/graph/disambig_tid.int \nfstminimizeencoded \nfstisstochastic exp/tri1/graph/HCLGa.fst \nadd-self-loops --self-loop-scale=0.1 --reorder=true exp/tri1/final.mdl \nrun.pl: job failed, log is in exp/tri1/decode/log/analyze_alignments.log\n'
It's really confusing that 'job failed' but actually training was oK.