Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.t5_vit5_base_vietnews_summarization_pipeline is a Vietnamese model originally trained by VietAI.
How to use
pipeline = PretrainedPipeline("t5_vit5_base_vietnews_summarization_pipeline", lang = "vi")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("t5_vit5_base_vietnews_summarization_pipeline", lang = "vi")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | t5_vit5_base_vietnews_summarization_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | vi |
| Size: | 537.3 MB |
References
https://huggingface.co/VietAI/vit5-base-vietnews-summarization
Included Models
- DocumentAssembler
- T5Transformer