hello everyone
i'm trying to create a language model for arabic digits only so i have created a knowledgebase using the online lmtool then i followed the tutorial here
i don't have enough recordings so my settings are :
$CFG_CD_TRAIN = 'no';
$CFG_INITIAL_NUM_DENSITIES = 8;
$CFG_FINAL_NUM_DENSITIES = 8;
but when i tried to decode the project i got this message
SENTENCE ERROR: 100.0% WORD ERROR RATE: 100.0%
i have attached my project here in the attachment
please help
hello everyone
i'm trying to create a language model for arabic digits only so i have created a knowledgebase using the online lmtool then i followed the tutorial here
i don't have enough recordings so my settings are :
$CFG_CD_TRAIN = 'no';
$CFG_INITIAL_NUM_DENSITIES = 8;
$CFG_FINAL_NUM_DENSITIES = 8;
but when i tried to decode the project i got this message
SENTENCE ERROR: 100.0% WORD ERROR RATE: 100.0%
i have attached my project here in the attachment
please help
It does not work for Arabic.