Description
Pretrained VisionEncoderDecoderForImageCaptioning, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.trocr_medieval_humanistica_pipeline is a French model originally trained by medieval-data.
How to use
pipeline = PretrainedPipeline("trocr_medieval_humanistica_pipeline", lang = "fr")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("trocr_medieval_humanistica_pipeline", lang = "fr")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | trocr_medieval_humanistica_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | fr |
| Size: | 1.4 GB |
References
https://huggingface.co/medieval-data/trocr-medieval-humanistica
Included Models
- ImageAssembler
- VisionEncoderDecoderForImageCaptioning