Description
Pretrained BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_base_swedish_cased_nepal_bhasa_pipeline is a Swedish model originally trained by KBLab.
How to use
pipeline = PretrainedPipeline("bert_base_swedish_cased_nepal_bhasa_pipeline", lang = "sv")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("bert_base_swedish_cased_nepal_bhasa_pipeline", lang = "sv")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | bert_base_swedish_cased_nepal_bhasa_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | sv |
| Size: | 504.9 MB |
References
https://huggingface.co/KBLab/bert-base-swedish-cased-new
Included Models
- DocumentAssembler
- TokenizerModel
- BertEmbeddings