Description
Pretrained BertSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sent_convbert_base_generator_finnish_pipeline is a Finnish model originally trained by Finnish-NLP.
How to use
pipeline = PretrainedPipeline("sent_convbert_base_generator_finnish_pipeline", lang = "fi")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("sent_convbert_base_generator_finnish_pipeline", lang = "fi")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | sent_convbert_base_generator_finnish_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | fi |
| Size: | 181.9 MB |
References
https://huggingface.co/Finnish-NLP/convbert-base-generator-finnish
Included Models
- DocumentAssembler
- TokenizerModel
- SentenceDetectorDLModel
- BertSentenceEmbeddings