Description
Pretrained DistilBertForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.distilbert_urdu_ner_pipeline is a Urdu model originally trained by blaikhole.
How to use
pipeline = PretrainedPipeline("distilbert_urdu_ner_pipeline", lang = "ur")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("distilbert_urdu_ner_pipeline", lang = "ur")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | distilbert_urdu_ner_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ur |
| Size: | 247.3 MB |
References
https://huggingface.co/blaikhole/distilbert-urdu-ner
Included Models
- DocumentAssembler
- TokenizerModel
- DistilBertForTokenClassification