In Ethiopia, Deaf peoples are vastly increase in number. Sign language is a natural languagernmostly used by Deaf persons to communicate with each other. However, during communicationrnthere is a big challenge between Deaf and normal person. Deaf use sign for communicationrnwhereas normal person use speech/text for communication.rnWe need efficient system to exchange sign to speech/text or speech/text to sign. This thesis workrnfocus on development of word level Amharic sign language recognition, translates Amharicrnword sign into their corresponding Amharic text using deep learning approach. The input for thernsystem is video frames of Amharic sign words and the final output of the system is Amharic text.rnThe proposed system has three major components: preprocessing, feature extraction andrnclassification. Two preprocessing steeps were used, cropping and RGB to Grayscale conversion.rnFeature extraction was done by using deep residual network (ResNet-34) and store in .csvrnformat.rnFinally, classification was done by the same deep learning algorithms ResNet-34. The system isrntrained and tested using a dataset prepared for this thesis purpose only for all Amharic signrnwords. The performance of the model measured by four different matrices (precision, recall, F1rnscore and accuracy).rnThe system classify 60 sign words and score overall accuracy of 95%. Therefore, thernclassification performance of ResNet-34 is very good.