Juicer is a decoder for HMM-based large vocabulary speech recognition that uses a weighted finite state transducer (WFST) representation of the search space. The package consists of a number of command line utilities: the Juicer decoder itself, along with a number of tools and scripts that are used to combine the various ASR knowledge sources (language model, pronunciation dictionary, acoustic models) into a single, optimised WFST that is input to the decoder.