I trained a model for Pocketsphinx with Voxforge audio files. I tested with (ps 0.5.1/ sb 0.4.1).
I get this error when executing pocketsphinx_continous with my model:
INFO: dict.c(232): Allocating 20 placeholders for new OOVs
ERROR: "dict.c", line 556: '=PLCHLDR0=': Unknown phone 'SIL'
ERROR: "dict.c", line 243: Failed to add DUMMY(SIL) entry to dictionary
would be glad for some help.
thanks
Sebastian
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
In my phoneset all phones were in lower case, only the phone SIL was in upper case.
The solution was to change all phones to upper case. Now decoding works pretty good :).
Changing only one phone back to lower case it results this "unknown phone" error from the decoder.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I trained a model for Pocketsphinx with Voxforge audio files. I tested with (ps 0.5.1/ sb 0.4.1).
I get this error when executing pocketsphinx_continous with my model:
INFO: dict.c(232): Allocating 20 placeholders for new OOVs
ERROR: "dict.c", line 556: '=PLCHLDR0=': Unknown phone 'SIL'
ERROR: "dict.c", line 243: Failed to add DUMMY(SIL) entry to dictionary
would be glad for some help.
thanks
Sebastian
In my phoneset all phones were in lower case, only the phone SIL was in upper case.
The solution was to change all phones to upper case. Now decoding works pretty good :).
Changing only one phone back to lower case it results this "unknown phone" error from the decoder.
Great that this issue is resolved. For usual lowercase phones you can use -dictcase decoder flag btw.
The phoneset of your model must have phone SIL (In upper case). I'm not sure what you don't understand in this message.