Translate English to Marathi Pipeline

Description

Marian is an efficient, free Neural Machine Translation framework written in pure C++ with minimal dependencies. It is mainly being developed by the Microsoft Translator team. Many academic (most notably the University of Edinburgh and in the past the Adam Mickiewicz University in Poznań) and commercial contributors help with its development. It is currently the engine behind the Microsoft Translator Neural Machine Translation services and being deployed by many companies, organizations and research projects (see below for an incomplete list).

source languages: en

target languages: mr

Live Demo Open in Colab Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("translate_en_mr", lang = "xx") 

pipeline.annotate("Your sentence to translate!")

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val pipeline = new PretrainedPipeline("translate_en_mr", lang = "xx")

pipeline.annotate("Your sentence to translate!")

import nlu
text = ["Your sentence to translate!"]

translate_df = nlu.load('xx.English.translate_to.Marathi').predict(text, output_level='sentence')
translate_df

Results

+------------------------------+--------------------------+
|sentence                      |translation               |
+------------------------------+--------------------------+
|Your sentence to translate!   |तू तुझ्या वाक्याचा अनुवाद करशील!  | 
+------------------------------+--------------------------+

Model Information

Model Name: translate_en_mr
Type: pipeline
Compatibility: Spark NLP 3.1.0+
License: Open Source
Edition: Official
Language: xx

Data Source

https://github.com/Helsinki-NLP/OPUS-MT-train/tree/master/models

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • MarianTransformer