Edit on GitHub
  • John Snow Labs
  • Jun 24, 2025

German distilbert_base_german_cased_pipeline pipeline DistilBertEmbeddings from distilbert

  • de
  • open_source
  • pipeline
  • onnx

Description

Pretrained DistilBertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.distilbert_base_german_cased_pipeline is a German model originally trained by distilbert.

Predicted Entities

Download Copy S3 URI

How to use

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

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

Model Information

Model Name: distilbert_base_german_cased_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: de
Size: 250.3 MB

References

References

https://huggingface.co/distilbert/distilbert-base-german-cased

Included Models

  • DocumentAssembler
  • TokenizerModel
  • DistilBertEmbeddings