Description
Pretrained MarianTransformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.iwslt17_marian_big_ctx0_cwd0_english_french_pipeline is a English model originally trained by context-mt.
How to use
pipeline = PretrainedPipeline("iwslt17_marian_big_ctx0_cwd0_english_french_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("iwslt17_marian_big_ctx0_cwd0_english_french_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | iwslt17_marian_big_ctx0_cwd0_english_french_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 1.3 GB |
References
https://huggingface.co/context-mt/iwslt17-marian-big-ctx0-cwd0-en-fr
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- MarianTransformer