Edit on GitHub
  • John Snow Labs
  • Dec 18, 2024

Latin trocr_medieval_print_pipeline pipeline VisionEncoderDecoderForImageCaptioning from medieval-data

  • la
  • open_source
  • pipeline
  • onnx

Description

Pretrained VisionEncoderDecoderForImageCaptioning, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.trocr_medieval_print_pipeline is a Latin model originally trained by medieval-data.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("trocr_medieval_print_pipeline", lang = "la")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("trocr_medieval_print_pipeline", lang = "la")
val annotations = pipeline.transform(df)

Model Information

Model Name: trocr_medieval_print_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: la
Size: 1.4 GB

References

https://huggingface.co/medieval-data/trocr-medieval-print

Included Models

  • ImageAssembler
  • VisionEncoderDecoderForImageCaptioning