Description
Pretrained XlmRoBertaSentenceEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.sent_tech_roberta_pipeline is a Vietnamese model originally trained by imta-ai.
How to use
pipeline = PretrainedPipeline("sent_tech_roberta_pipeline", lang = "vi")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("sent_tech_roberta_pipeline", lang = "vi")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | sent_tech_roberta_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | vi |
| Size: | 943.5 MB |
References
https://huggingface.co/imta-ai/tech-roberta
Included Models
- DocumentAssembler
- TokenizerModel
- SentenceDetectorDLModel
- XlmRoBertaSentenceEmbeddings