Edit model card

Model

Trained on Sonar corpus

Performance

Evaluated on dutch Euro Parl

              precision    recall  f1-score   support

           0   0.990421  0.994986  0.992698   9627605
           .   0.942931  0.948408  0.945662    433554
           ,   0.813030  0.773804  0.792932    379759
           ?   0.806700  0.790499  0.798518     13494
           -   0.606461  0.045317  0.084332     27341
           :   0.599856  0.501284  0.546158     18305

    accuracy                       0.981467  10500058
   macro avg   0.793233  0.675716  0.693383  10500058
weighted avg   0.980127  0.981467  0.980138  10500058

Usage:

pip install deepmultilingualpunctuation
from deepmultilingualpunctuation import PunctuationModel

model = PunctuationModel(model="oliverguhr/fullstop-dutch-sonar-punctuation-prediction")
text = "hervatting van de zitting ik verklaar de zitting van het europees parlement die op vrijdag 17 december werd onderbroken te zijn hervat"
result = model.restore_punctuation(text)
print(result)
Downloads last month
776
Hosted inference API
Token Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.