TensorflowMarian

MarianTransformer: Fast Neural Machine Translation

MarianTransformer uses models trained by MarianNMT.

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).

Sources : MarianNMT https://marian-nmt.github.io/ Marian: Fast Neural Machine Translation in C++ https://www.aclweb.org/anthology/P18-4020/

Linear Supertypes

Serializable, Serializable, AnyRef, Any

Instance Constructors

new TensorflowMarian(tensorflow: TensorflowWrapper, sppSrc: SentencePieceWrapper, sppTrg: SentencePieceWrapper, configProtoBytes: Option[Array[Byte]] = None, signatures: Option[Map[String, String]] = None)

tensorflow
LanguageDetectorDL Model wrapper with TensorFlow Wrapper
sppSrc
Contains the vocabulary for the target language.
sppTrg
Contains the vocabulary for the source language
configProtoBytes
Configuration for TensorFlow session

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
val _tfMarianSignatures: Map[String, String]
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def decode(sentences: Array[Array[Int]], vocabsArray: Array[String]): Seq[String]
def encode(sentences: Seq[Annotation], normalizer: MosesPunctNormalizer, maxSeqLength: Int, vocabsArray: Array[String], langId: Int, unknownTokenId: Int, eosTokenId: Int): Seq[Array[Int]]
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def generateSeq2Seq(sentences: Seq[Annotation], batchSize: Int = 10, maxInputLength: Int, maxOutputLength: Int, vocabs: Array[String], langId: String): Array[Annotation]

generate seq2seq via encoding, generating, and decoding
generate seq2seq via encoding, generating, and decoding
sentences
none empty Annotation
batchSize
size of baches to be process at the same time
maxInputLength
maximum length for input
maxOutputLength
maximum length for output
vocabs
list of all vocabs
langId
language id for multi-lingual models
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def process(batch: Seq[Array[Int]], maxOutputLength: Int, paddingTokenId: Int, eosTokenId: Int, vocabSize: Int): Array[Array[Int]]
val sppSrc: SentencePieceWrapper

Contains the vocabulary for the target language.
val sppTrg: SentencePieceWrapper

Contains the vocabulary for the source language
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
val tensorflow: TensorflowWrapper

LanguageDetectorDL Model wrapper with TensorFlow Wrapper
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Doc: package tensorflow

class TensorflowMarian extends Serializable

Instance Constructors

new TensorflowMarian(tensorflow: TensorflowWrapper, sppSrc: SentencePieceWrapper, sppTrg: SentencePieceWrapper, configProtoBytes: Option[Array[Byte]] = None, signatures: Option[Map[String, String]] = None)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

val _tfMarianSignatures: Map[String, String]

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def decode(sentences: Array[Array[Int]], vocabsArray: Array[String]): Seq[String]

def encode(sentences: Seq[Annotation], normalizer: MosesPunctNormalizer, maxSeqLength: Int, vocabsArray: Array[String], langId: Int, unknownTokenId: Int, eosTokenId: Int): Seq[Array[Int]]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

def generateSeq2Seq(sentences: Seq[Annotation], batchSize: Int = 10, maxInputLength: Int, maxOutputLength: Int, vocabs: Array[String], langId: String): Array[Annotation]

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def process(batch: Seq[Array[Int]], maxOutputLength: Int, paddingTokenId: Int, eosTokenId: Int, vocabSize: Int): Array[Array[Int]]

val sppSrc: SentencePieceWrapper

val sppTrg: SentencePieceWrapper

final def synchronized[T0](arg0: ⇒ T0): T0

val tensorflow: TensorflowWrapper

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped