VoiceTranslator

Introduction

This project is an simple translator app, created using Python and Django. The main assumption was to enable the speech capture and recognition.

The VoiceTranslator alows you to translate the standard typed text, and the speech captured with the microphone.

The application also allows users to register and log in. Each translation is saved in the integrated database, thanks to which the logged-in user has access to the history of his translations.

The application works based on the translation engine API - deepl, and the SpeechRecognition package.

The project has been created and tested using Python 3.10.7

The main goal of creating this project was to develop skills related to Django, and the audio recorder feature.

Setting up the environment

Use the package manager pip to install all the required libraries.

pip install -r requirements.txt

Add the .env file to the VoiceTranslator/VoiceTranslator directory. The structure of the .env file:

SECRET_KEY=""
DEEPL_API_KEY=""
TEMP_DIR=""
DB_NAME=""
DB_USER=""
DB_PASSWORD=""
DB_HOST=""
DB_PORT=""

The instance of postgresql database is required - in order to establish connection, please fill all the DB_... variables in the .env file accordingly to your DB instance.

Call the instructions below in order to prepare the database structure and load the supported languages.

python manage.py makemigrations translator
python manage.py migrate
python manage.py set_languages

Your environment is ready to use!

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT