Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.comet_t5_base_japanese_pipeline is a Japanese model originally trained by nlp-waseda.
How to use
pipeline = PretrainedPipeline("comet_t5_base_japanese_pipeline", lang = "ja")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("comet_t5_base_japanese_pipeline", lang = "ja")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | comet_t5_base_japanese_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ja |
| Size: | 948.1 MB |
References
https://huggingface.co/nlp-waseda/comet-t5-base-japanese
Included Models
- DocumentAssembler
- T5Transformer