This repository contains the models trained and used for Use Case 1: Sygeplejefagligudredning.
The purpose of the models are text classification and have been exposed to a test environment, where nurses from 11 municipalities have recorded and processed syntethic conversations in our prototype.
A plethora of experiments have been run throughout the projects lifespan, the two models published are the ones used specifically for live testing of the prototype. Information on each model can be found in their respective folder.
The following code can be used to load and use the model:
from setfit.modeling import SetFitModel
MODEL_PATH = 'path/to/model/'
MODEL_NAME = 'uc1_classification_model_afproevning2'
model = SetFitModel.from_pretrained(MODEL_PATH / MODEL_NAME)
model.predict('Dette er et test eksempel - indlæs eventuelt data fra projektet for eksempler på data')For more information about the project check the site: talegenkendelse.dk