Description
Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.distil_slovakbert_pipeline is a Slovak model originally trained by crabz.
How to use
pipeline = PretrainedPipeline("distil_slovakbert_pipeline", lang = "sk")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("distil_slovakbert_pipeline", lang = "sk")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | distil_slovakbert_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | sk |
| Size: | 305.7 MB |
References
https://huggingface.co/crabz/distil-slovakbert
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaEmbeddings