Description
Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.slovak_bpe_blm_pipeline is a Slovak model originally trained by daviddrzik.
How to use
pipeline = PretrainedPipeline("slovak_bpe_blm_pipeline", lang = "sk")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("slovak_bpe_blm_pipeline", lang = "sk")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | slovak_bpe_blm_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | sk |
| Size: | 219.6 MB |
References
https://huggingface.co/daviddrzik/SK_BPE_BLM
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaEmbeddings