Hidden Markov models (HMM) are a statistical approach frequently used to model linear sequences of observed events that depend on internal factors, but where the sequence of states that generate the observed events is unknown. HMMs are widely used for applications ranging from protein sequence classification to speech recognition. To facilitate the adoption of HMM, Fernando Moreno-Pino has released PyHHMM. PyHHMM contains Python implementations of Hidden Markov Models that support missing values and usage of heterogeneous data. In addition, PyHHMM implements both Akaike Information Criterion and Bayesian Information Criterion.