Most natural language processing systems use part-of-speech (POS) tagger as a separaternmodule in their architecture. Specially, it is very significant for developing parser, machinerntranslator, speech recognizer and search engines. Tagging is a process of labeling part-of speechrntags to words of a text such that contextual information can be obtained from wordrnlabels. The main aim of this study is to develop part-of-speech tagger for Afaan Oromo language.rnAfter reviewing literature on Afaan Oromo grammars and identifying tag set and wordrncategories, the study adopted Hidden Markov Model (HMM) approach and has implementedrnuni gram and bi gram models of vertebra algorithm. Uni gram model is used to understand wordrnambiguity in the language, while bi gram model is used to undertake contextual analysis ofrnwords. For training and testing purpose 159 sentences (with a total of 162 1 words) that are manuallyrnannotated sample corpus are used. The corpus is collected from different public Afaan Oromornnewspapers and bulletins to make the sample corpus balanced. A database of lexicalrnprobabilities (LexProb) and transitional probabilities (Trans Prob) are developed from thi srnannotated corpus. These two probabilities are from which the tagger learn and tag sequence ofrnwords in a sentence The performance of the prototype, Afaan Oromo tagger is tested using ten fold crossrnvalidation mechanism. The result shows that in both uni gram and bi gram models 87.58% andrn91.97% accuracy is obtained, respectively. Based on experimental analysis, concludingrnremarks and recommendations are forwarded.rnKeywords: Natural Language processing, parts of speech tagging, Hidden Markov Model, N - Gram.