Edit on GitHub
  • John Snow Labs
  • Feb 03, 2025

Marathi marathi_marh_least_haitian_1m_pipeline pipeline BertEmbeddings from l3cube-pune

  • mr
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.marathi_marh_least_haitian_1m_pipeline is a Marathi model originally trained by l3cube-pune.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("marathi_marh_least_haitian_1m_pipeline", lang = "mr")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("marathi_marh_least_haitian_1m_pipeline", lang = "mr")
val annotations = pipeline.transform(df)

Model Information

Model Name: marathi_marh_least_haitian_1m_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: mr
Size: 890.7 MB

References

https://huggingface.co/l3cube-pune/mr-least-ht-1m

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertEmbeddings