* corrected output names in DeepSpeech conversion doc * mo args correction * changed instruction for DeepSpeech version 0.8.2 * added venv activate; removed redundant ending * added picture and squashed MO graph input args into one * Apply suggestions from code review Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * applied review comments Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>