Description
Pretrained VisionEncoderDecoderForImageCaptioning, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.trocr_large_spanish_pipeline is a Castilian, Spanish model originally trained by qantev.
How to use
pipeline = PretrainedPipeline("trocr_large_spanish_pipeline", lang = "es")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("trocr_large_spanish_pipeline", lang = "es")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | trocr_large_spanish_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | es |
| Size: | 2.3 GB |
References
https://huggingface.co/qantev/trocr-large-spanish
Included Models
- ImageAssembler
- VisionEncoderDecoderForImageCaptioning