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

Turkish bert_base_turkish_128k_cased_qa_pipeline pipeline BertForQuestionAnswering from incidelen

  • tr
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_base_turkish_128k_cased_qa_pipeline is a Turkish model originally trained by incidelen.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("bert_base_turkish_128k_cased_qa_pipeline", lang = "tr")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("bert_base_turkish_128k_cased_qa_pipeline", lang = "tr")
val annotations = pipeline.transform(df)

Model Information

Model Name: bert_base_turkish_128k_cased_qa_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: tr
Size: 689.0 MB

References

https://huggingface.co/incidelen/bert-base-turkish-128k-cased-qa

Included Models

  • MultiDocumentAssembler
  • BertForQuestionAnswering