Hindi XLMRoBerta Embeddings (from neuralspace-reverie)

Description

Pretrained XLMRoBERTa Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. indic-transformers-hi-xlmroberta is a Hindi model orginally trained by neuralspace-reverie.

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = XlmRoBertaEmbeddings.pretrained("xlmroberta_embeddings_indic_transformers_hi_xlmroberta","hi") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings")
    
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["मुझे स्पार्क एनएलपी बहुत पसंद है"]]).toDF("text")

result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler() 
      .setInputCol("text") 
      .setOutputCol("document")
 
val tokenizer = new Tokenizer() 
    .setInputCols(Array("document"))
    .setOutputCol("token")

val embeddings = XlmRoBertaEmbeddings.pretrained("xlmroberta_embeddings_indic_transformers_hi_xlmroberta","hi") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("embeddings")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))

val data = Seq("मुझे स्पार्क एनएलपी बहुत पसंद है").toDF("text")

val result = pipeline.fit(data).transform(data)

Model Information

Model Name: xlmroberta_embeddings_indic_transformers_hi_xlmroberta
Compatibility: Spark NLP 3.4.4+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [embeddings]
Language: hi
Size: 505.0 MB
Case sensitive: true

References

  • https://huggingface.co/neuralspace-reverie/indic-transformers-hi-xlmroberta
  • https://oscar-corpus.com/