Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.t5_russian_text_normalization_v1_pipeline is a Russian model originally trained by CrabInHoney.
How to use
pipeline = PretrainedPipeline("t5_russian_text_normalization_v1_pipeline", lang = "ru")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("t5_russian_text_normalization_v1_pipeline", lang = "ru")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | t5_russian_text_normalization_v1_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ru |
| Size: | 228.0 MB |
References
https://huggingface.co/CrabInHoney/t5-ru-text-normalization-v1
Included Models
- DocumentAssembler
- T5Transformer