Description
Pretrained BertForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.persian_ner_parsbert_pipeline is a Persian model originally trained by PardisSzah.
How to use
pipeline = PretrainedPipeline("persian_ner_parsbert_pipeline", lang = "fa")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("persian_ner_parsbert_pipeline", lang = "fa")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | persian_ner_parsbert_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | fa |
| Size: | 606.5 MB |
References
https://huggingface.co/PardisSzah/Persian_NER_parsbert
Included Models
- DocumentAssembler
- TokenizerModel
- BertForTokenClassification