Marathi ALBERT Embeddings (from l3cube-pune)


Pretrained ALBERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. marathi-albert is a Marathi model orginally trained by l3cube-pune.


How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
embeddings = AlbertEmbeddings.pretrained("albert_embeddings_marathi_albert","mr") \
    .setInputCols(["document", "token"]) \
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["मला स्पार्क एनएलपी आवडते"]]).toDF("text")

result =
val documentAssembler = new DocumentAssembler() 
val tokenizer = new Tokenizer() 

val embeddings = AlbertEmbeddings.pretrained("albert_embeddings_marathi_albert","mr") 
    .setInputCols(Array("document", "token")) 

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

val data = Seq("मला स्पार्क एनएलपी आवडते").toDF("text")

val result =
import nlu
nlu.load("mr.embed.albert").predict("""मला स्पार्क एनएलपी आवडते""")

Model Information

Model Name: albert_embeddings_marathi_albert
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: mr
Size: 45.1 MB
Case sensitive: false