Simple Flask API around Pytorch model for identifying spoken language from speech
⚠ The app cannot really be run because the large language identification models are not included in this repository.
A client app that uses this API can be found here.
Clone the repository.
git clone https://github.com/jorgenvvv/lang-id-serverInstall the required packages.
pip install -r requirements.txtRename the config.example.py file to config.py and change the values if needed.
The model loading is done in the language_identifier.py file and some changes need to be made there. The paths that point to the model need to be modified.
Running the app in development mode can be done by executing the following commands
FLASK_APP=lang-id-server
FLASK_ENV=development
flask run --port 5005