Description
Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.roberta_base_indonesian_522m_pipeline is a Indonesian model originally trained by cahya.
How to use
pipeline = PretrainedPipeline("roberta_base_indonesian_522m_pipeline", lang = "id")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("roberta_base_indonesian_522m_pipeline", lang = "id")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | roberta_base_indonesian_522m_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | id |
| Size: | 470.8 MB |
References
https://huggingface.co/cahya/roberta-base-indonesian-522M
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaEmbeddings