Bert Punctuation Restoration Danish This model performs the punctuation restoration task in Danish. The method used is sequence classification similar to how NER models are trained. Model description TODO How to use The model requires some additional inference code, hence we created an awesome little pip package for inference. The inference code is based on the TokenClassificationPipeline pipeline from huggingface. First, install the little package by running Then restoration is as simple as the following snippet: Training data To Do Training procedure To Do Preprocessing TODO Evaluation results TODO
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy