Description
Pretrained BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.nepali_ner_bert_pipeline is a Nepali (macrolanguage) model originally trained by debabrata-ai.
How to use
pipeline = PretrainedPipeline("nepali_ner_bert_pipeline", lang = "ne")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("nepali_ner_bert_pipeline", lang = "ne")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | nepali_ner_bert_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ne |
| Size: | 663.2 MB |
References
https://huggingface.co/debabrata-ai/Nepali-NER-BERT
Included Models
- DocumentAssembler
- TokenizerModel
- BertEmbeddings