Description
sent_xlm_roberta_base_finetuned_swahili is a Swahili RoBERTa model obtained by fine-tuning xlm-roberta-base model on Swahili language texts. It provides better performance than the XLM-RoBERTa on named entity recognition datasets.
Specifically, this model is an xlm-roberta-base model that was fine-tuned on the Swahili corpus.
How to use
document = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentencerDL = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")\
.setInputCols(["document"])\
.setOutputCol("sentence")
sentece_embeddings = XlmRoBertaSentenceEmbeddings.pretrained("sent_xlm_roberta_base_finetuned_swahili", "sw")\
.setInputCols(["sentence"])\
.setOutputCol("sentence_embeddings")
val document = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")
.setInputCols("document")
.setOutputCol("sentence")
val senteceEmbeddings = XlmRoBertaSentenceEmbeddings.pretrained("sent_xlm_roberta_base_finetuned_swahili", "sw")
.setInputCols("sentence")
.setOutputCol("sentence_embeddings")
import nlu
nlu.load("sw.embed_sentence.xlm_roberta").predict("""Put your text here.""")
Model Information
| Model Name: | sent_xlm_roberta_base_finetuned_swahili |
| Compatibility: | Spark NLP 3.3.1+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence] |
| Output Labels: | [embeddings] |
| Language: | sw |
| Case sensitive: | true |
Data Source
Model is trained by David Adelani
Improted from https://huggingface.co/Davlan/xlm-roberta-base-finetuned-swahili