(There are NO Dependency Except Numpy) Dicrete and Mixture of Gaussian HMM and Bayesian HMM(离散和混合高斯隐马尔可夫模型和贝叶斯隐马尔可夫模型) Main Feature:

Three Basic Kinds of HMM Version: Dicrete and Continuous Bayesian Version

The Documentation For Bayesian Version HMM is Goldwater S, Griffiths T. A fully Bayesian approach to unsupervised part-of-speech tagging[C]//Annual meeting-association for computational linguistics. 2007, 45(1):744.(http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.379.8338&rep=rep1&type=pdf#page=782)

The Documentation For Dicrete and Continuous Version HMM is Rabiner L R. A tutorial on hidden Markov models and selected applications in speech recognition[J]. Proceedings of the IEEE, 1989, 77(2): 257-286.(http://www.robots.ox.ac.uk:5000/~vgg/rg/papers/hmm.pdf)

Also https://github.com/guyz/HMM is recommendable.