Keep failing in iteration 1

[Dan H]

I've succeeded twice with the training before. However, at this 3rd time (after adding new data), I keep getting this error:

$ sphinxtrain run
Sphinxtrain path: /usr/local/lib/sphinxtrain
Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
Running the training
MODULE: 000 Computing feature from audio files
Feature extraction is done
MODULE: 00 verify training files
    Phase 1: Checking to see if the dict and filler dict agrees with the phonelist file.
        Found 18800 words using 29 phones
    Phase 2: Checking to make sure there are not duplicate entries in the dictionary
    Phase 3: Check general format for the fileids file; utterance length (must be positive); files exist
    Phase 4: Checking number of lines in the transcript file should match lines in fileids file
    Phase 5: Determine amount of training data, see if n_tied_states seems reasonable.
        Estimated Total Hours Training: 5.81149444444445
        This is a small amount of data, no comment at this time
    Phase 6: Checking that all the words in the transcript are in the dictionary
        Words in dictionary: 18794
        Words in filler dictionary: 6
    Phase 7: Checking that all the phones in the transcript are in the phonelist, and all phones in the phonelist appear at least once
MODULE: 0000 train grapheme-to-phoneme model
Skipped (set $CFG_G2P_MODEL = 'yes' to enable)
MODULE: 01 Train LDA transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 02 Train MLLT transformation
Skipped (set $CFG_LDA_MLLT = 'yes' to enable)
MODULE: 05 Vector Quantization
Skipped for continuous models
MODULE: 10 Training Context Independent models for forced alignment and VTLN
Skipped:  $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
Skipped:  $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 11 Force-aligning transcripts
Skipped:  $ST::CFG_FORCEDALIGN set to 'no' in sphinx_train.cfg
MODULE: 12 Force-aligning data for VTLN
Skipped:  $ST::CFG_VTLN set to 'no' in sphinx_train.cfg
MODULE: 20 Training Context Independent models
    Phase 1: Cleaning up directories:
        accumulator...logs...qmanager...models...
    Phase 2: Flat initialize
    Phase 3: Forward-Backward
ERROR: Training failed in iteration 1

Having looked at the log files:

utt>     0          01-audio-01-1  468    0INFO: cvt2triphone.c(199): no multiphones defined, no conversion done
ERROR: "forward.c", line 594: All 2 active states, 63 64, zero at time 1
ERROR: "baum_welch.c", line 324: male1/01-audio-01-1 ignored
   168 0 
INFO: cmn.c(133): CMN: -387.67 64.52 -253.42 -235.65 83.31 -24.09 -30.89 94.15 303.87 -380.87 275.48 252.06 397.23 
ERROR: "forward.c", line 594: All 2 active states, 63 64, zero at time 1
ERROR: "baum_welch.c", line 324: male1/01-audio-01-2 ignored
utt>     1          01-audio-01-2 1213    0   412 0 
INFO: cmn.c(133): CMN: 627.87 -367.40 -776.83 -829.70 -417.78 763.99 -26.27 675.54 -540.51 -28.63 97.21 472.52 -733.19 
ERROR: "forward.c", line 594: All 2 active states, 63 64, zero at time 1
ERROR: "baum_welch.c", line 324: male1/01-audio-01-3 ignored
utt>     2          01-audio-01-3  617    0   196 0 

These audio samples above are even the succeeded ones in previous trainings. I confirmed all audios (including the new data) are using 16KHz, Mono, 16bit.

What could be the problem?

[Nickolay V. Shmyrev]

CMN values suggest that the input data format is wrong for those files. Check their format carefully, they are certainly not 16khz.