Description
Pretrained CamemBertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wangchanberta_thai_qa_pipeline is a Thai model originally trained by Thanakrit.
How to use
pipeline = PretrainedPipeline("wangchanberta_thai_qa_pipeline", lang = "th")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("wangchanberta_thai_qa_pipeline", lang = "th")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | wangchanberta_thai_qa_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | th |
| Size: | 392.1 MB |
References
https://huggingface.co/Thanakrit/wangchanberta-th-QA
Included Models
- MultiDocumentAssembler
- CamemBertForQuestionAnswering