small problem :
I made my "language model" with CMU-Cam_Toolkit_v2. When I test it, sphinx II says : "dictwid[10891] not in LM". Do you know
why?
Thanks
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
small problem :
I made my "language model" with CMU-Cam_Toolkit_v2. When I test it, sphinx II says : "dictwid[10891] not in LM". Do you know
why?
Thanks
One of the words in your dictionary (I am guessing at line 10891) is not in your LM.
the only word which is not in LM is <UNK>
*in dict
I verify, it is not that
In my dict I have 10891 words and the last is in my lm
I missed <s> and </s>
what are they ?
Begin and end utterance markers. Usually they are represented acoustically with background noise/silence models.
Thanks
others problems :
How to know the appartion's probability of each words