Edit on GitHub
  • John Snow Labs
  • Jul 29, 2024

Arabic t5_arat5_base_title_generation_pipeline pipeline T5Transformer from UBC-NLP

  • ar
  • open_source
  • pipeline
  • onnx

Description

Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.t5_arat5_base_title_generation_pipeline is a Arabic model originally trained by UBC-NLP.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("t5_arat5_base_title_generation_pipeline", lang = "ar")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("t5_arat5_base_title_generation_pipeline", lang = "ar")
val annotations = pipeline.transform(df)

Model Information

Model Name: t5_arat5_base_title_generation_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: ar
Size: 1.7 GB

References

https://huggingface.co/UBC-NLP/AraT5-base-title-generation

Included Models

  • DocumentAssembler
  • T5Transformer