Description
Pretrained RoBertaForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.tara_roberta_base_persian_farsi_qa_pipeline is a Persian model originally trained by hosseinhimself.
How to use
pipeline = PretrainedPipeline("tara_roberta_base_persian_farsi_qa_pipeline", lang = "fa")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("tara_roberta_base_persian_farsi_qa_pipeline", lang = "fa")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | tara_roberta_base_persian_farsi_qa_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | fa |
| Size: | 463.6 MB |
References
https://huggingface.co/hosseinhimself/tara-roberta-base-fa-qa
Included Models
- MultiDocumentAssembler
- RoBertaForQuestionAnswering