Skip to Main Content
Table 4: 

WER and CER values for CR with varying number of ConvNet layers trained using standard loss function.

eval–1eval–2
WERCERWERCER
CRk=1 6.18 2.15 3.72 1.29 
CRk=2 6.46 2.30 4.18 1.46 
CRk=3 6.47 2.26 3.61 1.26 
CRk=4 6.93 2.51 3.54 1.31 
CRk=5 6.63 2.40 3.92 1.38 
CRk=6 6.68 2.52 3.94 1.50 
CRk=7 6.58 2.60 3.90 1.50 
CRk=8 6.56 2.48 3.64 1.54 
CRk=9 6.59 2.69 3.84 1.60 
CRk=10 6.32 2.52 3.61 1.62 
eval–1eval–2
WERCERWERCER
CRk=1 6.18 2.15 3.72 1.29 
CRk=2 6.46 2.30 4.18 1.46 
CRk=3 6.47 2.26 3.61 1.26 
CRk=4 6.93 2.51 3.54 1.31 
CRk=5 6.63 2.40 3.92 1.38 
CRk=6 6.68 2.52 3.94 1.50 
CRk=7 6.58 2.60 3.90 1.50 
CRk=8 6.56 2.48 3.64 1.54 
CRk=9 6.59 2.69 3.84 1.60 
CRk=10 6.32 2.52 3.61 1.62 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy.
Accept