-
Notifications
You must be signed in to change notification settings - Fork 6
Mac Installation
These instructions were tested on a Mac running macOS Sierra Version 10.12.4.
In order to get OpenMM to work you need to have the following things installed...
In order to run OpenMM, you'll need to install Python 2.7 (Python 3 support is not available yet) and the following Python modules:
- numpy and scipy: packages for scientific computing
- pandas: package for data structures and data analysis
- speech_recognition: package for interacting with speech recognition APIs
You can install them all at once using pip:
pip install numpy scipy pandas SpeechRecognition
In order to use Covarep to extract acoustic features, you also need the 2017 Matlab Runtime version for your machine, which is free and available to download on their site.
In order to convert video to audio, you need to ffmpeg installed:
brew install ffmpeg
To perform visual feature extraction OpenMM requires OpenFace.
To extract syntactic features, which are part of the linguistic analysis, SyntaxNet parser is required. We suggest following these instructions to download. If you plan on working with German or Spanish data, make sure to also add those models to your Docker container. Here are the instructions for downloading the other language models.
After all the prerequisities and dependencies are installed successfully. You can install OpenMM by cloning this repo:
git clone https://github.com/michellemorales/OpenMM.git