spark-nlp 2.6.3rc1__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/audio/wav2vec2_for_ctc.py

@@ -0,0 +1,161 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+"""Contains classes concerning Wav2Vec2ForCTC."""
+
+from sparknlp.common import *
+
+
+class Wav2Vec2ForCTC(AnnotatorModel,
+                     HasBatchedAnnotateAudio,
+                     HasAudioFeatureProperties,
+                     HasEngine):
+    """Wav2Vec2 Model with a language modeling head on top for Connectionist Temporal
+    Classification (CTC). Wav2Vec2 was proposed in wav2vec 2.0: A Framework for
+    Self-Supervised Learning of Speech Representations by Alexei Baevski, Henry Zhou,
+    Abdelrahman Mohamed, Michael Auli.
+
+    The annotator takes audio files and transcribes it as text. The audio needs to be
+    provided pre-processed an array of floats.
+
+    Note that this annotator is currently not supported on Apple Silicon processors such
+    as the M1. This is due to the processor not supporting instructions for XLA.
+
+    Pretrained models can be loaded with ``pretrained`` of the companion object:
+
+    >>> speechToText = Wav2Vec2ForCTC.pretrained() \\
+    ...     .setInputCols(["audio_assembler"]) \\
+    ...     .setOutputCol("text")
+
+
+    The default model is ``"asr_wav2vec2_base_960h"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models>`__.
+
+    To see which models are compatible and how to import them see
+    https://github.com/JohnSnowLabs/spark-nlp/discussions/5669 and to see more extended
+    examples, see
+    `Wav2Vec2ForCTCTestSpec <https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/audio/Wav2Vec2ForCTCTestSpec.scala>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``AUDIO``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+
+    batchSize
+        Size of each batch, by default 2
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> audioAssembler = AudioAssembler() \\
+    ...     .setInputCol("audio_content") \\
+    ...     .setOutputCol("audio_assembler")
+    >>> speechToText = Wav2Vec2ForCTC \\
+    ...     .pretrained() \\
+    ...     .setInputCols(["audio_assembler"]) \\
+    ...     .setOutputCol("text")
+    >>> pipeline = Pipeline().setStages([audioAssembler, speechToText])
+    >>> processedAudioFloats = spark.createDataFrame([[rawFloats]]).toDF("audio_content")
+    >>> result = pipeline.fit(processedAudioFloats).transform(processedAudioFloats)
+    >>> result.select("text.result").show(truncate = False)
+    +------------------------------------------------------------------------------------------+
+    |result                                                                                    |
+    +------------------------------------------------------------------------------------------+
+    |[MISTER QUILTER IS THE APOSTLE OF THE MIDLE CLASES AND WE ARE GLAD TO WELCOME HIS GOSPEL ]|
+    +------------------------------------------------------------------------------------------+
+    """
+    name = "Wav2Vec2ForCTC"
+
+    inputAnnotatorTypes = [AnnotatorType.AUDIO]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with "
+                             "config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.audio.Wav2Vec2ForCTC",
+                 java_model=None):
+        super(Wav2Vec2ForCTC, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=2
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        Wav2Vec2ForCTC
+            The restored model
+        """
+        from sparknlp.internal import _Wav2Vec2ForCTC
+        jModel = _Wav2Vec2ForCTC(folder, spark_session._jsparkSession)._java_obj
+        return Wav2Vec2ForCTC(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="asr_wav2vec2_base_960h", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "asr_wav2vec2_base_960h"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        Wav2Vec2ForCTC
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(Wav2Vec2ForCTC, name, lang, remote_loc)

sparknlp/annotator/audio/whisper_for_ctc.py

@@ -0,0 +1,251 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+"""Contains classes concerning WhisperForCTC."""
+
+from sparknlp.common import *
+
+
+class WhisperForCTC(AnnotatorModel,
+                    HasBatchedAnnotateAudio,
+                    HasAudioFeatureProperties,
+                    HasEngine, HasGeneratorProperties):
+    """Whisper Model with a language modeling head on top for Connectionist Temporal Classification
+    (CTC).
+
+    Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of
+    multilingual and multitask supervised data collected from the web. It transcribe in multiple
+    languages, as well as translate from those languages into English.
+
+    The audio needs to be provided pre-processed an array of floats.
+
+    Note that at the moment, this annotator only supports greedy search and only Spark Versions
+    3.4 and up are supported.
+
+    For multilingual models, the language and the task (transcribe or translate) can be set with
+    ``setLanguage`` and ``setTask``.
+
+    Pretrained models can be loaded with ``pretrained`` of the companion object:
+
+    .. code-block:: python
+
+        speechToText = WhisperForCTC.pretrained() \\
+            .setInputCols(["audio_assembler"]) \\
+            .setOutputCol("text")
+
+
+    The default model is ``"asr_whisper_tiny_opt"``, if no name is provided.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models>`__.
+
+    To see which models are compatible and how to import them see
+    https://github.com/JohnSnowLabs/spark-nlp/discussions/5669 and to see more extended
+    examples, see
+    `WhisperForCTCTestSpec <https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/audio/WhisperForCTCTest.scala>`__.
+
+    **References:**
+
+    `Robust Speech Recognition via Large-Scale Weak Supervision <https://arxiv.org/abs/2212.04356>`__
+
+    **Paper Abstract:**
+
+    *We study the capabilities of speech processing systems trained simply to predict large
+    amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual
+    and multitask supervision, the resulting models generalize well to standard benchmarks and are
+    often competitive with prior fully supervised results but in a zero- shot transfer setting
+    without the need for any fine- tuning. When compared to humans, the models approach their
+    accuracy and robustness. We are releasing models and inference code to serve as a foundation
+    for further work on robust speech processing.*
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``AUDIO``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    task
+        The formatted task for the audio. Either `<|translate|>` or `<|transcribe|>`.
+    language
+        The language for the audio, formatted to e.g. `<|en|>`. Check the model description for
+        supported languages.
+    isMultilingual
+        Whether the model is multilingual
+    minOutputLength
+        Minimum length of the sequence to be generated
+    maxOutputLength
+        Maximum length of output text
+    doSample
+        Whether or not to use sampling; use greedy decoding otherwise
+    temperature
+        The value used to module the next token probabilities
+    topK
+        The number of highest probability vocabulary tokens to keep for top-k-filtering
+    topP
+        If set to float < 1, only the most probable tokens with probabilities that add up to ``top_p`` or higher are
+        kept for generation
+    repetitionPenalty
+        The parameter for repetition penalty. 1.0 means no penalty.
+        See `this paper <https://arxiv.org/pdf/1909.05858.pdf>`__ for more details
+    noRepeatNgramSize
+        If set to int > 0, all ngrams of that size can only occur once
+    beamSize
+        The Number of beams for beam search
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> audioAssembler = AudioAssembler() \\
+    ...     .setInputCol("audio_content") \\
+    ...     .setOutputCol("audio_assembler")
+    >>> speechToText = WhisperForCTC.pretrained() \\
+    ...     .setInputCols(["audio_assembler"]) \\
+    ...     .setOutputCol("text")
+    >>> pipeline = Pipeline().setStages([audioAssembler, speechToText])
+    >>> processedAudioFloats = spark.createDataFrame([[rawFloats]]).toDF("audio_content")
+    >>> result = pipeline.fit(processedAudioFloats).transform(processedAudioFloats)
+    >>> result.select("text.result").show(truncate = False)
+    +------------------------------------------------------------------------------------------+
+    |result                                                                                    |
+    +------------------------------------------------------------------------------------------+
+    |[ Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.]|
+    +------------------------------------------------------------------------------------------+
+    """
+    name = "WhisperForCTC"
+
+    inputAnnotatorTypes = [AnnotatorType.AUDIO]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with "
+                             "config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    language = Param(Params._dummy(), "language", "Optional parameter to set the language for the transcription.",
+                     typeConverter=TypeConverters.toString)
+
+    isMultilingual = Param(Params._dummy(), "isMultilingual", "Whether the model is multilingual.",
+                           typeConverter=TypeConverters.toBoolean)
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    def getLanguage(self):
+        """Gets the langauge for the transcription."""
+        return self.getOrDefault(self.language)
+
+    def getIsMultilingual(self):
+        """Gets whether the model is multilingual."""
+        return self.getOrDefault(self.isMultilingual)
+
+    def setLanguage(self, value):
+        """Sets the language for the audio, formatted to e.g. `<|en|>`. Check the model description for
+        supported languages.
+
+        Parameters
+        ----------
+        value : String
+            Formatted language code
+        """
+        return self._call_java("setLanguage", value)
+
+    def setTask(self, value):
+        """Sets the formatted task for the audio. Either `<|translate|>` or `<|transcribe|>`.
+
+        Only multilingual models can do translation.
+
+        Parameters
+        ----------
+        value : String
+            Formatted task
+        """
+        return self._call_java("setTask", value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.audio.WhisperForCTC",
+                 java_model=None):
+        super(WhisperForCTC, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            minOutputLength=0,
+            maxOutputLength=448,
+            doSample=False,
+            temperature=1.0,
+            topK=1,
+            topP=1.0,
+            repetitionPenalty=1.0,
+            noRepeatNgramSize=0,
+            batchSize=2,
+            beamSize=1,
+            nReturnSequences=1,
+            isMultilingual=True,
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        WhisperForCTC
+            The restored model
+        """
+        from sparknlp.internal import _WhisperForCTC
+        jModel = _WhisperForCTC(folder, spark_session._jsparkSession)._java_obj
+        return WhisperForCTC(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="asr_whisper_tiny_opt", lang="xx", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "asr_hubert_large_ls960"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        WhisperForCTC
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(WhisperForCTC, name, lang, remote_loc)

sparknlp/annotator/chunk2_doc.py

@@ -0,0 +1,85 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Contains classes for Chunk2Doc."""
+
+from pyspark import keyword_only
+
+from sparknlp.common import AnnotatorProperties
+from sparknlp.common.annotator_type import AnnotatorType
+from sparknlp.internal import AnnotatorTransformer
+
+
+class Chunk2Doc(AnnotatorTransformer, AnnotatorProperties):
+    """Converts a ``CHUNK`` type column back into ``DOCUMENT``.
+    
+    Useful when trying to re-tokenize or do further analysis on a ``CHUNK`` result.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``CHUNK``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    None
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.pretrained import PretrainedPipeline
+
+    Location entities are extracted and converted back into ``DOCUMENT`` type for
+    further processing.
+
+    >>> data = spark.createDataFrame([[1, "New York and New Jersey aren't that far apart actually."]]).toDF("id", "text")
+
+    Define pretrained pipeline that extracts Named Entities amongst other things
+    and apply `Chunk2Doc` on it.
+
+    >>> pipeline = PretrainedPipeline("explain_document_dl")
+    >>> chunkToDoc = Chunk2Doc().setInputCols("entities").setOutputCol("chunkConverted")
+    >>> explainResult = pipeline.transform(data)
+
+    Show results.
+
+    >>> result = chunkToDoc.transform(explainResult)
+    >>> result.selectExpr("explode(chunkConverted)").show(truncate=False)
+    +------------------------------------------------------------------------------+
+    |col                                                                           |
+    +------------------------------------------------------------------------------+
+    |[document, 0, 7, New York, [entity -> LOC, sentence -> 0, chunk -> 0], []]    |
+    |[document, 13, 22, New Jersey, [entity -> LOC, sentence -> 0, chunk -> 1], []]|
+    +------------------------------------------------------------------------------+
+
+    See Also
+    --------
+    Doc2Chunk : for converting `DOCUMENT` annotations to `CHUNK`
+    """
+
+    name = "Chunk2Doc"
+
+    inputAnnotatorTypes = [AnnotatorType.CHUNK]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    @keyword_only
+    def __init__(self):
+        super(Chunk2Doc, self).__init__(classname="com.johnsnowlabs.nlp.annotators.Chunk2Doc")
+
+    @keyword_only
+    def setParams(self):
+        kwargs = self._input_kwargs
+        return self._set(**kwargs)

sparknlp/annotator/chunker.py

@@ -0,0 +1,137 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Contains classes for the Chunker."""
+from sparknlp.common import *
+
+
+class Chunker(AnnotatorModel):
+    """This annotator matches a pattern of part-of-speech tags in order to
+    return meaningful phrases from document. Extracted part-of-speech tags are
+    mapped onto the sentence, which can then be parsed by regular expressions.
+    The part-of-speech tags are wrapped by angle brackets ``<>`` to be easily
+    distinguishable in the text itself.
+
+    This example sentence will result in the form:
+
+    .. code-block:: none
+
+        "Peter Pipers employees are picking pecks of pickled peppers."
+        "<NNP><NNP><NNS><VBP><VBG><NNS><IN><JJ><NNS><.>"
+
+
+    To then extract these tags, ``regexParsers`` need to be set with e.g.:
+
+    >>> chunker = Chunker() \\
+    ...    .setInputCols(["sentence", "pos"]) \\
+    ...    .setOutputCol("chunk") \\
+    ...    .setRegexParsers(["<NNP>+", "<NNS>+"])
+
+    When defining the regular expressions, tags enclosed in angle brackets are
+    treated as groups, so here specifically ``"<NNP>+"`` means 1 or more nouns
+    in succession.
+
+    For more extended examples see the `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/chunking/Chunk_Extraction_with_Chunker.ipynb>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT, POS``      ``CHUNK``
+    ====================== ======================
+
+    Parameters
+    ----------
+    regexParsers
+        An array of grammar based chunk parsers
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> sentence = SentenceDetector() \\
+    ...     .setInputCols("document") \\
+    ...     .setOutputCol("sentence")
+    >>> tokenizer = Tokenizer() \\
+    ...     .setInputCols(["sentence"]) \\
+    ...     .setOutputCol("token")
+    >>> POSTag = PerceptronModel.pretrained() \\
+    ...     .setInputCols("document", "token") \\
+    ...     .setOutputCol("pos")
+    >>> chunker = Chunker() \\
+    ...     .setInputCols("sentence", "pos") \\
+    ...     .setOutputCol("chunk") \\
+    ...     .setRegexParsers(["<NNP>+", "<NNS>+"])
+    >>> pipeline = Pipeline() \\
+    ...     .setStages([
+    ...       documentAssembler,
+    ...       sentence,
+    ...       tokenizer,
+    ...       POSTag,
+    ...       chunker
+    ...     ])
+    >>> data = spark.createDataFrame([["Peter Pipers employees are picking pecks of pickled peppers."]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(chunk) as result").show(truncate=False)
+    +-------------------------------------------------------------+
+    |result                                                       |
+    +-------------------------------------------------------------+
+    |[chunk, 0, 11, Peter Pipers, [sentence -> 0, chunk -> 0], []]|
+    |[chunk, 13, 21, employees, [sentence -> 0, chunk -> 1], []]  |
+    |[chunk, 35, 39, pecks, [sentence -> 0, chunk -> 2], []]      |
+    |[chunk, 52, 58, peppers, [sentence -> 0, chunk -> 3], []]    |
+    +-------------------------------------------------------------+
+
+    See Also
+    --------
+    PerceptronModel : for Part-Of-Speech tagging
+    """
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.POS]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    regexParsers = Param(Params._dummy(),
+                         "regexParsers",
+                         "an array of grammar based chunk parsers",
+                         typeConverter=TypeConverters.toListString)
+
+    name = "Chunker"
+
+    @keyword_only
+    def __init__(self):
+        super(Chunker, self).__init__(classname="com.johnsnowlabs.nlp.annotators.Chunker")
+
+    def setRegexParsers(self, value):
+        """Sets an array of grammar based chunk parsers.
+
+        POS classes should be enclosed in angle brackets, then treated as
+        groups.
+
+        Parameters
+        ----------
+        value : List[str]
+            Array of grammar based chunk parsers
+
+
+        Examples
+        --------
+        >>> chunker = Chunker() \\
+        ...     .setInputCols("sentence", "pos") \\
+        ...     .setOutputCol("chunk") \\
+        ...     .setRegexParsers(["<NNP>+", "<NNS>+"])
+        """
+        return self._set(regexParsers=value)