Edit on GitHub
  • John Snow Labs
  • Jan 23, 2025

Latin sent_xlm_roberta_base_latin_uncased_pipeline pipeline XlmRoBertaSentenceEmbeddings from Cicciokr

  • la
  • open_source
  • pipeline
  • onnx

Description

Pretrained XlmRoBertaSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sent_xlm_roberta_base_latin_uncased_pipeline is a Latin model originally trained by Cicciokr.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("sent_xlm_roberta_base_latin_uncased_pipeline", lang = "la")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("sent_xlm_roberta_base_latin_uncased_pipeline", lang = "la")
val annotations = pipeline.transform(df)

Model Information

Model Name: sent_xlm_roberta_base_latin_uncased_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: la
Size: 916.7 MB

References

https://huggingface.co/Cicciokr/XLM-Roberta-Base-Latin-Uncased

Included Models

  • DocumentAssembler
  • TokenizerModel
  • SentenceDetectorDLModel
  • XlmRoBertaSentenceEmbeddings