Description
Pretrained BartTransformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.barticzech_1_0_pipeline is a Czech model originally trained by UWB-AIR.
How to use
pipeline = PretrainedPipeline("barticzech_1_0_pipeline", lang = "cs")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("barticzech_1_0_pipeline", lang = "cs")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | barticzech_1_0_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | cs |
| Size: | 1.9 GB |
References
https://huggingface.co/UWB-AIR/barticzech-1.0
Included Models
- DocumentAssembler
- BartTransformer