Edit on GitHub
  • John Snow Labs
  • Sep 01, 2024

German roberta_base_wechsel_german_pipeline pipeline RoBertaEmbeddings from benjamin

  • de
  • open_source
  • pipeline
  • onnx

Description

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

Download Copy S3 URI

How to use


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



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

Model Information

Model Name: roberta_base_wechsel_german_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: de
Size: 465.8 MB

References

https://huggingface.co/benjamin/roberta-base-wechsel-german

Included Models

  • DocumentAssembler
  • TokenizerModel
  • RoBertaEmbeddings