Edit on GitHub
  • John Snow Labs
  • Aug 22, 2024

Multilingual mt5_base_multilingual_summarization_multilarge_czech_smesum_pipeline pipeline T5Transformer from ctu-aic

  • xx
  • open_source
  • pipeline
  • onnx

Description

Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mt5_base_multilingual_summarization_multilarge_czech_smesum_pipeline is a Multilingual model originally trained by ctu-aic.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("mt5_base_multilingual_summarization_multilarge_czech_smesum_pipeline", lang = "xx")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("mt5_base_multilingual_summarization_multilarge_czech_smesum_pipeline", lang = "xx")
val annotations = pipeline.transform(df)

Model Information

Model Name: mt5_base_multilingual_summarization_multilarge_czech_smesum_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: xx
Size: 6.0 MB

References

https://huggingface.co/ctu-aic/mt5-base-multilingual-summarization-multilarge-cs-smesum

Included Models

  • DocumentAssembler
  • T5Transformer