pocketsphinx-hmm-wsj1 0.5.1+dfsg1-0ubuntu2 (armel binary) in ubuntu precise

 PocketSphinx is a lightweight, cross-platform, speaker-independent,
 large-vocabulary continuous speech recognition engine.
 .
 This package contains the default acoustic model for PocketSphinx.
 It was trained from 180 hours of speech, recorded on a close-talking
 microphone and downsampled to 8kHz.