Edit on GitHub
  • John Snow Labs
  • Mar 30, 2025

Multilingual interlingua_multilingual_original_script_roberta_pipeline pipeline RoBertaEmbeddings from ibm

  • xx
  • open_source
  • pipeline
  • onnx

Description

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

Predicted Entities

Download Copy S3 URI

How to use

pipeline = PretrainedPipeline("interlingua_multilingual_original_script_roberta_pipeline", lang = "xx")
annotations =  pipeline.transform(df)

val pipeline = new PretrainedPipeline("interlingua_multilingual_original_script_roberta_pipeline", lang = "xx")
val annotations = pipeline.transform(df)

Model Information

Model Name: interlingua_multilingual_original_script_roberta_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: xx
Size: 638.6 MB

References

References

https://huggingface.co/ibm/ia-multilingual-original-script-roberta

Included Models

  • DocumentAssembler
  • TokenizerModel
  • RoBertaEmbeddings