The mathematical model is offered to describe an algorithm for functioning of a speech rhythm. The duration of a speech signal is divided into the numbered sequence of durations of voice and voiceless segments. All elements of this sequence will be considered as values normalized on the maximum element. We determine this sequence of the elements as a speech rhythm. 1) The model describes a speech rhythm as the recurrent relations between elements of a rhythm. 2) The model permits use of the concept of information entropy. 3) The model explains experimental findings obtained by our research group during comparative investigation of a rhythm in normal speech and stuttering. In particular, the model explains the existence of two classes of stutterers with various rhythms of speech.