Description
Pretrained MarianTransformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.marian_maltese_rom_romanian_pipeline is a Moldavian, Moldovan, Romanian model originally trained by IoanRazvan.
How to use
pipeline = PretrainedPipeline("marian_maltese_rom_romanian_pipeline", lang = "ro")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("marian_maltese_rom_romanian_pipeline", lang = "ro")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | marian_maltese_rom_romanian_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ro |
| Size: | 509.1 MB |
References
https://huggingface.co/IoanRazvan/marian_mt_rom_ro
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- MarianTransformer