Description
Pretrained XlmRoBertaEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.hindi_roberta is a Hindi model originally trained by l3cube-pune.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
embeddings = XlmRoBertaEmbeddings.pretrained("hindi_roberta","hi") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")
pipeline = Pipeline().setStages([documentAssembler, tokenizer, embeddings])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")
val embeddings = XlmRoBertaEmbeddings.pretrained("hindi_roberta","hi")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
val data = Seq("I love spark-nlp").toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | hindi_roberta |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [xlm_roberta] |
| Language: | hi |
| Size: | 1.0 GB |
References
https://huggingface.co/l3cube-pune/hindi-roberta