Edit on GitHub
  • John Snow Labs
  • Sep 01, 2024

Thai wangchanberta_qa_thaiqa_squad_pipeline pipeline CamemBertForQuestionAnswering from Thammarak

  • th
  • open_source
  • pipeline
  • onnx

Description

Pretrained CamemBertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wangchanberta_qa_thaiqa_squad_pipeline is a Thai model originally trained by Thammarak.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wangchanberta_qa_thaiqa_squad_pipeline", lang = "th")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("wangchanberta_qa_thaiqa_squad_pipeline", lang = "th")
val annotations = pipeline.transform(df)

Model Information

Model Name: wangchanberta_qa_thaiqa_squad_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: th
Size: 392.1 MB

References

https://huggingface.co/Thammarak/wangchanBERTa-QA-thaiqa_squad

Included Models

  • MultiDocumentAssembler
  • CamemBertForQuestionAnswering