Edit on GitHub
  • John Snow Labs
  • Apr 07, 2025

German sent_bert_base_token_dropping_dewiki_v1_pipeline pipeline BertSentenceEmbeddings from gwlms

  • de
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sent_bert_base_token_dropping_dewiki_v1_pipeline is a German model originally trained by gwlms.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("sent_bert_base_token_dropping_dewiki_v1_pipeline", lang = "de")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("sent_bert_base_token_dropping_dewiki_v1_pipeline", lang = "de")
val annotations = pipeline.transform(df)

Model Information

Model Name: sent_bert_base_token_dropping_dewiki_v1_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: de
Size: 412.9 MB

References

https://huggingface.co/gwlms/bert-base-token-dropping-dewiki-v1

Included Models

  • DocumentAssembler
  • TokenizerModel
  • SentenceDetectorDLModel
  • BertSentenceEmbeddings