Sinhala, Sinhalese sinhala_roberta_pipeline pipeline RoBertaEmbeddings from flax-community

Description

Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sinhala_roberta_pipeline is a Sinhala, Sinhalese model originally trained by flax-community.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("sinhala_roberta_pipeline", lang = "si")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("sinhala_roberta_pipeline", lang = "si")
val annotations = pipeline.transform(df)

Model Information

Model Name: sinhala_roberta_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: si
Size: 464.5 MB

References

https://huggingface.co/flax-community/Sinhala-roberta

Included Models

  • DocumentAssembler
  • TokenizerModel
  • RoBertaEmbeddings