I am in step of Acoustic modelling for speech recognition using sphinx,.. I got several warnings like this:
*
WARNING: This phone (DD) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (DH) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (F) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (J) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (K) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (KH) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (M) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
*
Why this?? How can I solve this??
This is a sharable link of database... Please help.....
WARNING:Thisphone(\u200DDD)occursinthedictionary(/home/shmyrev/t/etc/Malayalam.dic), but not in the phonelist (/home/shmyrev/t/etc/Malayalam.phone)WARNING:Thisphone(\u200DDH)occursinthedictionary(/home/shmyrev/t/etc/Malayalam.dic), but not in the phonelist (/home/shmyrev/t/etc/Malayalam.phone)WARNING:Thisphone(\u200DF)occursinthedictionary(/home/shmyrev/t/etc/Malayalam.dic), but not in the phonelist (/home/shmyrev/t/etc/Malayalam.phone)WARNING:Thisphone(\u200DJ)occursinthedictionary(/home/shmyrev/t/etc/Malayalam.dic), but not in the phonelist (/home/shmyrev/t/etc/Malayalam.phone)WARNING:Thisphone(K)occursinthedictionary(/home/shmyrev/t/etc/Malayalam.dic), but not in the phonelist (/home/shmyrev/t/etc/Ma
You have extra symbols in the dictionary, for example in this line:
നിര്ദേശങ്ങ NN I R EE \u200DDD E S A NG A
നിര്ദേശങ്ങള് NN I R EE \u200DDD E S A NG A LL EE\u200D
Note the red dots with hex code E2 80 8D called zero width joiner (http://www.fileformat.info/info/unicode/char/200d/index.htm)
You need to remove this symbol from the dictionary.
Last edit: Nickolay V. Shmyrev 2016-11-09
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
I am in step of Acoustic modelling for speech recognition using sphinx,.. I got several warnings like this:
*
WARNING: This phone (DD) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (DH) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (F) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (J) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (K) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (KH) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
WARNING: This phone (M) occurs in the dictionary (/home/adspr/sphinx4/Malayalam/etc/Malayalam.dic), but not in the phonelist (/home/adspr/sphinx4/Malayalam/etc/Malayalam.phone)
*
Why this?? How can I solve this??
This is a sharable link of database... Please help.....
https://drive.google.com/open?id=0B_74UylilDfCd2ZscmJ0OVZKX1U
Thank You....
Actually errors are different:
You have extra symbols in the dictionary, for example in this line:
Note the red dots with hex code E2 80 8D called zero width joiner (http://www.fileformat.info/info/unicode/char/200d/index.htm)
You need to remove this symbol from the dictionary.
Last edit: Nickolay V. Shmyrev 2016-11-09
Okay sir,,, I solved it...
Thank you....