Source code for synapse.ml.cognitive.speech.SpeechToText

# Copyright (C) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See LICENSE in project root for information.


import sys
if sys.version >= '3':
    basestring = str

from pyspark import SparkContext, SQLContext
from pyspark.sql import DataFrame
from pyspark.ml.param.shared import *
from pyspark import keyword_only
from pyspark.ml.util import JavaMLReadable, JavaMLWritable
from synapse.ml.core.platform import running_on_synapse_internal
from synapse.ml.core.serialize.java_params_patch import *
from pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.evaluation import JavaEvaluator
from pyspark.ml.common import inherit_doc
from synapse.ml.core.schema.Utils import *
from pyspark.ml.param import TypeConverters
from synapse.ml.core.schema.TypeConversionUtils import generateTypeConverter, complexTypeConverter


[docs]@inherit_doc class SpeechToText(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer): """ Args: AADToken (object): AAD Token used for authentication CustomAuthHeader (object): A Custom Value for Authorization Header audioData (object): The data sent to the service must be a .wav files concurrency (int): max number of concurrent calls concurrentTimeout (float): max number seconds to wait on futures if concurrency >= 1 errorCol (str): column to hold http errors format (object): Specifies the result format. Accepted values are simple and detailed. Default is simple. handler (object): Which strategy to use when handling requests language (object): Identifies the spoken language that is being recognized. outputCol (str): The name of the output column profanity (object): Specifies how to handle profanity in recognition results. Accepted values are masked, which replaces profanity with asterisks, removed, which remove all profanity from the result, or raw, which includes the profanity in the result. The default setting is masked. subscriptionKey (object): the API key to use timeout (float): number of seconds to wait before closing the connection url (str): Url of the service """ AADToken = Param(Params._dummy(), "AADToken", "ServiceParam: AAD Token used for authentication") CustomAuthHeader = Param(Params._dummy(), "CustomAuthHeader", "ServiceParam: A Custom Value for Authorization Header") audioData = Param(Params._dummy(), "audioData", "ServiceParam: The data sent to the service must be a .wav files ") concurrency = Param(Params._dummy(), "concurrency", "max number of concurrent calls", typeConverter=TypeConverters.toInt) concurrentTimeout = Param(Params._dummy(), "concurrentTimeout", "max number seconds to wait on futures if concurrency >= 1", typeConverter=TypeConverters.toFloat) errorCol = Param(Params._dummy(), "errorCol", "column to hold http errors", typeConverter=TypeConverters.toString) format = Param(Params._dummy(), "format", "ServiceParam: Specifies the result format. Accepted values are simple and detailed. Default is simple. ") handler = Param(Params._dummy(), "handler", "Which strategy to use when handling requests") language = Param(Params._dummy(), "language", "ServiceParam: Identifies the spoken language that is being recognized. ") outputCol = Param(Params._dummy(), "outputCol", "The name of the output column", typeConverter=TypeConverters.toString) profanity = Param(Params._dummy(), "profanity", "ServiceParam: Specifies how to handle profanity in recognition results. Accepted values are masked, which replaces profanity with asterisks, removed, which remove all profanity from the result, or raw, which includes the profanity in the result. The default setting is masked. ") subscriptionKey = Param(Params._dummy(), "subscriptionKey", "ServiceParam: the API key to use") timeout = Param(Params._dummy(), "timeout", "number of seconds to wait before closing the connection", typeConverter=TypeConverters.toFloat) url = Param(Params._dummy(), "url", "Url of the service", typeConverter=TypeConverters.toString) @keyword_only def __init__( self, java_obj=None, AADToken=None, AADTokenCol=None, CustomAuthHeader=None, CustomAuthHeaderCol=None, audioData=None, audioDataCol=None, concurrency=1, concurrentTimeout=None, errorCol="SpeechToText_2d122c6ee4e0_error", format=None, formatCol=None, handler=None, language=None, languageCol=None, outputCol="SpeechToText_2d122c6ee4e0_output", profanity=None, profanityCol=None, subscriptionKey=None, subscriptionKeyCol=None, timeout=60.0, url=None ): super(SpeechToText, self).__init__() if java_obj is None: self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.cognitive.speech.SpeechToText", self.uid) else: self._java_obj = java_obj self._setDefault(concurrency=1) self._setDefault(errorCol="SpeechToText_2d122c6ee4e0_error") self._setDefault(outputCol="SpeechToText_2d122c6ee4e0_output") self._setDefault(timeout=60.0) if hasattr(self, "_input_kwargs"): kwargs = self._input_kwargs else: kwargs = self.__init__._input_kwargs if java_obj is None: for k,v in kwargs.items(): if v is not None: getattr(self, "set" + k[0].upper() + k[1:])(v)
[docs] @keyword_only def setParams( self, AADToken=None, AADTokenCol=None, CustomAuthHeader=None, CustomAuthHeaderCol=None, audioData=None, audioDataCol=None, concurrency=1, concurrentTimeout=None, errorCol="SpeechToText_2d122c6ee4e0_error", format=None, formatCol=None, handler=None, language=None, languageCol=None, outputCol="SpeechToText_2d122c6ee4e0_output", profanity=None, profanityCol=None, subscriptionKey=None, subscriptionKeyCol=None, timeout=60.0, url=None ): """ Set the (keyword only) parameters """ if hasattr(self, "_input_kwargs"): kwargs = self._input_kwargs else: kwargs = self.__init__._input_kwargs return self._set(**kwargs)
[docs] @classmethod def read(cls): """ Returns an MLReader instance for this class. """ return JavaMMLReader(cls)
[docs] @staticmethod def getJavaPackage(): """ Returns package name String. """ return "com.microsoft.azure.synapse.ml.cognitive.speech.SpeechToText"
@staticmethod def _from_java(java_stage): module_name=SpeechToText.__module__ module_name=module_name.rsplit(".", 1)[0] + ".SpeechToText" return from_java(java_stage, module_name)
[docs] def setAADToken(self, value): """ Args: AADToken: AAD Token used for authentication """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setAADToken(value) return self
[docs] def setAADTokenCol(self, value): """ Args: AADToken: AAD Token used for authentication """ self._java_obj = self._java_obj.setAADTokenCol(value) return self
[docs] def setCustomAuthHeader(self, value): """ Args: CustomAuthHeader: A Custom Value for Authorization Header """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setCustomAuthHeader(value) return self
[docs] def setCustomAuthHeaderCol(self, value): """ Args: CustomAuthHeader: A Custom Value for Authorization Header """ self._java_obj = self._java_obj.setCustomAuthHeaderCol(value) return self
[docs] def setAudioData(self, value): """ Args: audioData: The data sent to the service must be a .wav files """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setAudioData(value) return self
[docs] def setAudioDataCol(self, value): """ Args: audioData: The data sent to the service must be a .wav files """ self._java_obj = self._java_obj.setAudioDataCol(value) return self
[docs] def setConcurrency(self, value): """ Args: concurrency: max number of concurrent calls """ self._set(concurrency=value) return self
[docs] def setConcurrentTimeout(self, value): """ Args: concurrentTimeout: max number seconds to wait on futures if concurrency >= 1 """ self._set(concurrentTimeout=value) return self
[docs] def setErrorCol(self, value): """ Args: errorCol: column to hold http errors """ self._set(errorCol=value) return self
[docs] def setFormat(self, value): """ Args: format: Specifies the result format. Accepted values are simple and detailed. Default is simple. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setFormat(value) return self
[docs] def setFormatCol(self, value): """ Args: format: Specifies the result format. Accepted values are simple and detailed. Default is simple. """ self._java_obj = self._java_obj.setFormatCol(value) return self
[docs] def setHandler(self, value): """ Args: handler: Which strategy to use when handling requests """ self._set(handler=value) return self
[docs] def setLanguage(self, value): """ Args: language: Identifies the spoken language that is being recognized. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setLanguage(value) return self
[docs] def setLanguageCol(self, value): """ Args: language: Identifies the spoken language that is being recognized. """ self._java_obj = self._java_obj.setLanguageCol(value) return self
[docs] def setOutputCol(self, value): """ Args: outputCol: The name of the output column """ self._set(outputCol=value) return self
[docs] def setProfanity(self, value): """ Args: profanity: Specifies how to handle profanity in recognition results. Accepted values are masked, which replaces profanity with asterisks, removed, which remove all profanity from the result, or raw, which includes the profanity in the result. The default setting is masked. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setProfanity(value) return self
[docs] def setProfanityCol(self, value): """ Args: profanity: Specifies how to handle profanity in recognition results. Accepted values are masked, which replaces profanity with asterisks, removed, which remove all profanity from the result, or raw, which includes the profanity in the result. The default setting is masked. """ self._java_obj = self._java_obj.setProfanityCol(value) return self
[docs] def setSubscriptionKey(self, value): """ Args: subscriptionKey: the API key to use """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setSubscriptionKey(value) return self
[docs] def setSubscriptionKeyCol(self, value): """ Args: subscriptionKey: the API key to use """ self._java_obj = self._java_obj.setSubscriptionKeyCol(value) return self
[docs] def setTimeout(self, value): """ Args: timeout: number of seconds to wait before closing the connection """ self._set(timeout=value) return self
[docs] def setUrl(self, value): """ Args: url: Url of the service """ self._set(url=value) return self
[docs] def getAADToken(self): """ Returns: AADToken: AAD Token used for authentication """ return self._java_obj.getAADToken()
[docs] def getCustomAuthHeader(self): """ Returns: CustomAuthHeader: A Custom Value for Authorization Header """ return self._java_obj.getCustomAuthHeader()
[docs] def getAudioData(self): """ Returns: audioData: The data sent to the service must be a .wav files """ return self._java_obj.getAudioData()
[docs] def getConcurrency(self): """ Returns: concurrency: max number of concurrent calls """ return self.getOrDefault(self.concurrency)
[docs] def getConcurrentTimeout(self): """ Returns: concurrentTimeout: max number seconds to wait on futures if concurrency >= 1 """ return self.getOrDefault(self.concurrentTimeout)
[docs] def getErrorCol(self): """ Returns: errorCol: column to hold http errors """ return self.getOrDefault(self.errorCol)
[docs] def getFormat(self): """ Returns: format: Specifies the result format. Accepted values are simple and detailed. Default is simple. """ return self._java_obj.getFormat()
[docs] def getHandler(self): """ Returns: handler: Which strategy to use when handling requests """ return self.getOrDefault(self.handler)
[docs] def getLanguage(self): """ Returns: language: Identifies the spoken language that is being recognized. """ return self._java_obj.getLanguage()
[docs] def getOutputCol(self): """ Returns: outputCol: The name of the output column """ return self.getOrDefault(self.outputCol)
[docs] def getProfanity(self): """ Returns: profanity: Specifies how to handle profanity in recognition results. Accepted values are masked, which replaces profanity with asterisks, removed, which remove all profanity from the result, or raw, which includes the profanity in the result. The default setting is masked. """ return self._java_obj.getProfanity()
[docs] def getSubscriptionKey(self): """ Returns: subscriptionKey: the API key to use """ return self._java_obj.getSubscriptionKey()
[docs] def getTimeout(self): """ Returns: timeout: number of seconds to wait before closing the connection """ return self.getOrDefault(self.timeout)
[docs] def getUrl(self): """ Returns: url: Url of the service """ return self.getOrDefault(self.url)
[docs] def setCustomServiceName(self, value): self._java_obj = self._java_obj.setCustomServiceName(value) return self
[docs] def setEndpoint(self, value): self._java_obj = self._java_obj.setEndpoint(value) return self
[docs] def setDefaultInternalEndpoint(self, value): self._java_obj = self._java_obj.setDefaultInternalEndpoint(value) return self
def _transform(self, dataset: DataFrame) -> DataFrame: if running_on_synapse_internal(): try: from synapse.ml.fabric.token_utils import TokenUtils from synapse.ml.fabric.service_discovery import get_fabric_env_config fabric_env_config = get_fabric_env_config().fabric_env_config if self._java_obj.getInternalServiceType() != "openai": self._java_obj.setDefaultAADToken(TokenUtils().get_aad_token()) else: self._java_obj.setDefaultCustomAuthHeader(TokenUtils().get_openai_auth_header()) self.setDefaultInternalEndpoint(fabric_env_config.get_mlflow_workload_endpoint()) except ModuleNotFoundError as e: pass return super()._transform(dataset)
[docs] def setLocation(self, value): self._java_obj = self._java_obj.setLocation(value) return self
[docs] def setLinkedService(self, value): self._java_obj = self._java_obj.setLinkedService(value) return self