Edit on GitHub
  • John Snow Labs
  • Feb 03, 2025

German ner_newsagency_bert_german_pipeline pipeline BertForTokenClassification from impresso-project

  • de
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.ner_newsagency_bert_german_pipeline is a German model originally trained by impresso-project.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("ner_newsagency_bert_german_pipeline", lang = "de")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("ner_newsagency_bert_german_pipeline", lang = "de")
val annotations = pipeline.transform(df)

Model Information

Model Name: ner_newsagency_bert_german_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: de
Size: 407.0 MB

References

https://huggingface.co/impresso-project/ner-newsagency-bert-de

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertForTokenClassification