sphinxtrain run - run into problem

[Jens Kallup]

only one ERROR:
No word from the language model has pronunciation in the dictionary
What is wrong?
How to fix?
Jens

console output (snippet) :

MODULE: DECODE Decoding using models previously trained
        Decoding 7 segments starting at 0 (part 1 of 1) 
        0% 
ERROR: This step had 1 ERROR messages and 0 WARNING messages.  Please check the log file for details.
        Aligning results to find error rate
        SENTENCE ERROR: 0.0% (0/7)   WORD ERROR RATE: 0.0% (0/9)

vocdeu.dic

A               a
ACHT            acht
B               b
DATEI           datei
DER             der
SPEICHERN       speichern

#vocdeu.lm
#############################################################################
## Copyright (c) 1996, Carnegie Mellon University, Cambridge University,
## Ronald Rosenfeld and Philip Clarkson
## Version 3, Copyright (c) 2006, Carnegie Mellon University 
## Contributors includes Wen Xu, Ananlada Chotimongkol, 
## David Huggins-Daines, Arthur Chan and Alan Black 
#############################################################################
=============================================================================
===============  This file was produced by the CMU-Cambridge  ===============
===============     Statistical Language Modeling Toolkit     ===============
=============================================================================
This is a 3-gram language model, based on a vocabulary of 9 words,
  which begins "</s>", "<s>", "A"...
This is a CLOSED-vocabulary model
  (OOVs eliminated from training data and are forbidden in test data)
Good-Turing discounting was applied.
1-gram frequency of frequency : 3 
2-gram frequency of frequency : 3 0 0 0 0 0 0 
3-gram frequency of frequency : 3 0 0 0 0 0 0 
1-gram discounting ratios : 0.33 
2-gram discounting ratios : 
3-gram discounting ratios : 
This file is in the ARPA-standard format introduced by Doug Paul.

p(wd3|wd1,wd2)= if(trigram exists)           p_3(wd1,wd2,wd3)
                else if(bigram w1,w2 exists) bo_wt_2(w1,w2)*p(wd3|wd2)
                else                         p(wd3|w2)

p(wd2|wd1)= if(bigram exists) p_2(wd1,wd2)
            else              bo_wt_1(wd1)*p_1(wd2)

All probs and back-off weights (bo_wt) are given in log10 form.

Data formats:

Beginning of data mark: \data\
ngram 1=nr            # number of 1-grams
ngram 2=nr            # number of 2-grams
ngram 3=nr            # number of 3-grams

\1-grams:
p_1     wd_1 bo_wt_1
\2-grams:
p_2     wd_1 wd_2 bo_wt_2
\3-grams:
p_3     wd_1 wd_2 wd_3 

end of data mark: \end\

\data\
ngram 1=9
ngram 2=3
ngram 3=3

\1-grams:
-0.9542 </s>    -0.4260
-0.9542 <s> -0.4260
-0.9542 A   -0.4260
-0.9542 ACHT    0.0000
-0.9542 B   0.0000
-0.9542 DATEI   0.0000
-0.9542 DER 0.0000
-0.9542 SIL 0.0000
-0.9542 SPEICHERN   0.0000

\2-grams:
-0.1761 </s> <s> 0.1761
-0.1761 <s> A 0.1761
-0.1761 A ACHT -0.2499

\3-grams:
-0.3010 </s> <s> A 
-0.3010 <s> A ACHT 
-0.3010 A ACHT B 

\end\

[Nickolay V. Shmyrev]

It is better to provide a complete log, not just error message. For now it's not quite clear what happened there but I suspect you used different dictionary.