Menu

PocketSphinx decoder init failed for sinhala language

Help
ab1984
2015-08-10
2015-08-11
  • ab1984

    ab1984 - 2015-08-10

    I have error occure at the end of the sphinxtrain process.
    When it starts to decode the content it gives me the following error,

    **MODULE: DECODE Decoding using models previously trained
    Decoding 4936 segments starting at 0 (part 1 of 1)
    0% ERROR: FATAL: "batch.c", line 821: PocketSphinx decoder init failed

    ERROR: This step had 3 ERROR messages and 0 WARNING messages. Please check the log file for details.
    ERROR: Failed to start pocketsphinx_batch
    Aligning results to find error rate
    Can't open /home/bopagama/Desktop/Workspace/sentence/result/sentence-1-1.match
    word_align.pl failed with error code 65280 at /usr/local/lib/sphinxtrain/scripts/decode/slave.pl line 173.**

    I have check the tutorial and also I was able to successfully complete training for an4 data base data.
    Once I check the log file HERE and as per my understanding sphinxtrain requires binary format (.lm.dmp) of the language model but for the sinhala language SRILM (Language modeling toolkit I used) doesn't support for that.

    What can I do for this issue?

    Is their any setting changes need to make to correct this issue?

    Thank You

     

    Last edit: ab1984 2015-08-10
  • ab1984

    ab1984 - 2015-08-10

    Anyone any ideas please?

     
  • Nickolay V. Shmyrev

    Please update pocketsphinx and sphinxbase, there is an issue importing SRILM models, it should be fixed now.

     
  • ab1984

    ab1984 - 2015-08-11

    Thank You Nickolay

    Can I use the packages in http://cmusphinx.sourceforge.net/wiki/download

    Are they up to date?

    Or
    Is their any commands to run to update pocketshinx and sphinxbase in linux?

    I'm new to this. that is why I'm asking these questions.

    Thank You

     
  • ab1984

    ab1984 - 2015-08-11

    awesome thank you very much nickolay

     
  • ketan kandi

    ketan kandi - 2017-11-02

    Dear ,

    PLEASE DO NOT IGNORE THIS PROBLEM. I AM RUNNING OUT OF TIME :(

    I am currently working on my project of Marathi language speech recognition.
    It worked perfectly after the execution of "sphinxtrain run" command ,but I am getting this error again and again
    after the execution of following command in linux operating system

    sphinxtrain -s decode run

    even after trying solutions from the above forums and many other forums .
    The error is:

    Sphinxtrain path: /usr/local/lib/sphinxtrain
    Sphinxtrain binaries path: /usr/local/libexec/sphinxtrain
    MODULE: DECODE Decoding using models previously trained
    Decoding 49 segments starting at 0 (part 1 of 1)
    0%
    ERROR: This step had 3 ERROR messages and 0 WARNING messages. Please check the log file for details.
    Aligning results to find error rate
    Can't open /root/Desktop/MiPr/speech_recognition/Marathi/result/Marathi-1-1.match
    word_align.pl failed with error code 65280 at /usr/local/lib/sphinxtrain/scripts/decode/slave.pl line 173.

    I am attaching my logdir file with this comment
    http://www.mediafire.com/file/3du0r863md04n10/logdir.zip
    anyone who can solve this please come to me with feasible solution.
    thank you :)

     

Log in to post a comment.

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.