Skip to content

jhauswald/lucida

 
 

Repository files navigation

Lucida

Lucida is a speech and vision based intelligent personal assistant inspired by Sirius. Visit the provided readmes in lucida for instructions to build Lucida and follow the instructions to build lucida-suite here. Post to Lucida-users for more information and answers to questions. The project is released under BSD license, except certain submodules contain their own specific licensing information. We would love to have your help on improving Lucida, and see CONTRIBUTING for more details.

Lucida Local Development

  • From this directory, type: make local. This will run scripts in tools/ to install all the required depedencies. Note: if you would like to install the packages locally, each install script must be modified accordingly. This will also build lucida-suite and lucida.
  • Similar to what is set in the Makefile, you must set a few environment variables. From the top directory:
export THRIFT_ROOT=`pwd`/tools/thrift-0.9.2
export CAFFE=`pwd`/tools/caffe/distribute
export LUCIDAROOT=`pwd`/lucida
  • Start all the services using supervisord:
cd tools
supervisord -c lucida.conf
  • To test, in another terminal navigate to lucida/commandcenter and use the following commands (replacing (PORT) with 8090 as defined in lucida.conf):
# Test image matching, speech recognition, and question-answering
./ccclient --asr <AUDIO_FILE> --imm <IMAGE_FILE> (PORT)
# Test speech recognition, and question-answering
./ccclient --asr <AUDIO_FILE> (PORT)
# Test question-answering
./ccclient --qa <QUESTION> (PORT)
  • The above example uses a small test database for the QA system. To use all of Wikipedia:
cd tools;
./download_wiki_index.sh # make sure to set INDRI_INDEX as recommended

Then restart all the services.

Lucida Docker Deployment

Note: Instructions to download and build Sirius can be found at http://sirius.clarity-lab.org

About

Speech and Vision Based Intelligent Personal Assistant

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Java 68.0%
  • C++ 24.1%
  • Cuda 1.8%
  • Makefile 1.6%
  • Python 1.3%
  • C 1.2%
  • Other 2.0%