Description
Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.roberta_embeddings_amharic_roberta_pipeline is a Amharic model originally trained by uhhlt.
How to use
pipeline = PretrainedPipeline("roberta_embeddings_amharic_roberta_pipeline", lang = "am")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("roberta_embeddings_amharic_roberta_pipeline", lang = "am")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | roberta_embeddings_amharic_roberta_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | am |
| Size: | 1.6 GB |
References
https://huggingface.co/uhhlt/am-roberta
Included Models
- DocumentAssembler
- TokenizerModel
- RoBertaEmbeddings