Edit on GitHub
  • John Snow Labs
  • Aug 06, 2024

Chinese chinese_spelling_correction_t5_pipeline pipeline T5Transformer from CodeTed

  • zh
  • open_source
  • pipeline
  • onnx

Description

Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.chinese_spelling_correction_t5_pipeline is a Chinese model originally trained by CodeTed.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("chinese_spelling_correction_t5_pipeline", lang = "zh")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("chinese_spelling_correction_t5_pipeline", lang = "zh")
val annotations = pipeline.transform(df)

Model Information

Model Name: chinese_spelling_correction_t5_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: zh
Size: 1.1 GB

References

https://huggingface.co/CodeTed/Chinese_Spelling_Correction_T5

Included Models

  • DocumentAssembler
  • T5Transformer