Menu

Force Alignment Training Error Sphinx3

Help
2016-03-03
2016-03-04
  • Senjam Shantirani

    I am training using Sphinx3 , with TIMIT data.
    While running the RullAll, when the FA Module starts, it does not run.
    "$ST::CFG_SCRIPT_DIR/03.force_align/slave_align.pl",

    The log file has the following error, please help me identify what the problem is:

    INFO: feat.c(1148): At directory /home/PhoneModel/workspace/hmm/feat
    INFO: feat.c(378): Reading mfc file: '/home/PhoneModel/workspace/hmm/feat/TRAIN_DR1_FCJF0_SA2.mfc'[0..-1]
    INFO: cmn.c(175): CMN: 11.85 1.20 -1.53 0.64 -0.82 -0.11 -0.38 -0.18 -0.08 -0.13 -0.14 -0.17 0.05
    INFO: main_align.c(1009): TRAIN_DR1_FCJF0_SA2: 215 input frames
    ERROR: "main_align.c", line 891: Final state not reached; no alignment for TRAIN_DR1_FCJF0_SA2

    INFO: corpus.c(661): TRAIN_DR1_FCJF0_SA2: 0.6 sec CPU, 0.6 sec Clk; TOT: 1.5 sec CPU, 1.5 sec Clk

    What is the meaning the Final state not reached; and what may be the problem and how to solve it?

    Thanking you in advance,
    Shanti

     
  • Senjam Shantirani

    Thank you Nickolay.

     

Log in to post a comment.