Description
Pretrained BertSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sent_bert_base_german_uncased_pipeline is a German model originally trained by voize.
How to use
pipeline = PretrainedPipeline("sent_bert_base_german_uncased_pipeline", lang = "de")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("sent_bert_base_german_uncased_pipeline", lang = "de")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | sent_bert_base_german_uncased_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | de |
| Size: | 410.4 MB |
References
https://huggingface.co/voize/bert-base-german-uncased
Included Models
- DocumentAssembler
- TokenizerModel
- SentenceDetectorDLModel
- BertSentenceEmbeddings