Description
Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.nsina_headlines_mt5_base_pipeline is a Sinhala, Sinhalese model originally trained by sinhala-nlp.
How to use
pipeline = PretrainedPipeline("nsina_headlines_mt5_base_pipeline", lang = "si")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("nsina_headlines_mt5_base_pipeline", lang = "si")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | nsina_headlines_mt5_base_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | si |
| Size: | 2.3 GB |
References
https://huggingface.co/sinhala-nlp/NSINA-Headlines-mt5-base
Included Models
- DocumentAssembler
- T5Transformer