Using cloud speech recognition in low bandwidth environments
portaudio package for using stream.py
Install for macOS using Homebrew
brew install portaudio
python3 -m folder_name.filename
- Clone project
git clone https://github.com/chezecz/research-project.git
- Install dependencies
pip install -r requirements.txt
- Set enviroment variables
FLASK_ENV=development
FLASK_APP=server
(Optional) Google Cloud API key
export GOOGLE_APPLICATION_CREDENTIALS=$PATH_TO_FILE/api_key.json
- Launch Flask server
flask run
By Default: Server is located on http://127.0.0.1:5000/ or http://localhost:5000/
- (Optional) Upload necessary files into resources folder
- Set your Google Cloud API Key
export GOOGLE_APPLICATION_CREDENTIALS=$PATH_TO_FILE/api_key.json
-
Run Application
a. Client application
python3 client.py [filename]
b. Run Stream Application for recording microphone
python3 stream.py