azure-ai-transcription 1.0.0b1__py3-none-any.whl

azure/ai/transcription/models/_models.py

@@ -0,0 +1,450 @@
+# coding=utf-8
+# --------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License. See License.txt in the project root for license information.
+# Code generated by Microsoft (R) Python Code Generator.
+# Changes may cause incorrect behavior and will be lost if the code is regenerated.
+# --------------------------------------------------------------------------
+# pylint: disable=useless-super-delegation
+
+from typing import Any, Mapping, Optional, TYPE_CHECKING, Union, overload
+
+from .._utils.model_base import Model as _Model, rest_field
+from .._utils.utils import FileType
+
+if TYPE_CHECKING:
+    from .. import models as _models
+
+
+class ChannelCombinedPhrases(_Model):
+    """The full transcript per channel.
+
+    :ivar channel: The 0-based channel index. Only present if channel separation is enabled.
+    :vartype channel: int
+    :ivar text: The complete transcribed text for the channel. Required.
+    :vartype text: str
+    """
+
+    channel: Optional[int] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The 0-based channel index. Only present if channel separation is enabled."""
+    text: str = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The complete transcribed text for the channel. Required."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        text: str,
+        channel: Optional[int] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class EnhancedModeProperties(_Model):
+    """Enhanced mode properties for transcription.
+
+    :ivar enabled: Enable enhanced mode for transcription. This is automatically set to true when
+     task, targetLanguage, or prompt are specified.
+    :vartype enabled: bool
+    :ivar task: Task type for enhanced mode.
+    :vartype task: str
+    :ivar target_language: Target language for enhanced mode.
+    :vartype target_language: str
+    :ivar prompt: A list of user prompts.
+    :vartype prompt: list[str]
+    """
+
+    enabled: Optional[bool] = rest_field(visibility=["read"])
+    """Enable enhanced mode for transcription. This is automatically set to true when task,
+     targetLanguage, or prompt are specified."""
+    task: Optional[str] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """Task type for enhanced mode."""
+    target_language: Optional[str] = rest_field(
+        name="targetLanguage", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Target language for enhanced mode."""
+    prompt: Optional[list[str]] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """A list of user prompts."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        task: Optional[str] = None,
+        target_language: Optional[str] = None,
+        prompt: Optional[list[str]] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class PhraseListProperties(_Model):
+    """Phrase list properties for transcription.
+
+    :ivar phrases: List of phrases for recognition.
+    :vartype phrases: list[str]
+    :ivar biasing_weight: Biasing weight for phrase list (1.0 to 20.0).
+    :vartype biasing_weight: float
+    """
+
+    phrases: Optional[list[str]] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """List of phrases for recognition."""
+    biasing_weight: Optional[float] = rest_field(
+        name="biasingWeight", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Biasing weight for phrase list (1.0 to 20.0)."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        phrases: Optional[list[str]] = None,
+        biasing_weight: Optional[float] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class TranscribedPhrase(_Model):
+    """A transcribed phrase.
+
+    :ivar channel: The 0-based channel index. Only present if channel separation is enabled.
+    :vartype channel: int
+    :ivar speaker: A unique integer number that is assigned to each speaker detected in the audio
+     without particular order. Only present if speaker diarization is enabled.
+    :vartype speaker: int
+    :ivar offset_milliseconds: The start offset of the phrase in milliseconds. Required.
+    :vartype offset_milliseconds: int
+    :ivar duration_milliseconds: The duration of the phrase in milliseconds. Required.
+    :vartype duration_milliseconds: int
+    :ivar text: The transcribed text of the phrase. Required.
+    :vartype text: str
+    :ivar words: The words that make up the phrase. Only present if word-level timestamps are
+     enabled.
+    :vartype words: list[~azure.ai.transcription.models.TranscribedWord]
+    :ivar locale: The locale of the phrase.
+    :vartype locale: str
+    :ivar confidence: The confidence value for the phrase. Required.
+    :vartype confidence: float
+    """
+
+    channel: Optional[int] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The 0-based channel index. Only present if channel separation is enabled."""
+    speaker: Optional[int] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """A unique integer number that is assigned to each speaker detected in the audio without
+     particular order. Only present if speaker diarization is enabled."""
+    offset_milliseconds: int = rest_field(
+        name="offsetMilliseconds", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The start offset of the phrase in milliseconds. Required."""
+    duration_milliseconds: int = rest_field(
+        name="durationMilliseconds", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The duration of the phrase in milliseconds. Required."""
+    text: str = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The transcribed text of the phrase. Required."""
+    words: Optional[list["_models.TranscribedWord"]] = rest_field(
+        visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The words that make up the phrase. Only present if word-level timestamps are enabled."""
+    locale: Optional[str] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The locale of the phrase."""
+    confidence: float = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The confidence value for the phrase. Required."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        offset_milliseconds: int,
+        duration_milliseconds: int,
+        text: str,
+        confidence: float,
+        channel: Optional[int] = None,
+        speaker: Optional[int] = None,
+        words: Optional[list["_models.TranscribedWord"]] = None,
+        locale: Optional[str] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class TranscribedWord(_Model):
+    """Time-stamped word in the display form.
+
+    :ivar text: The recognized word, including punctuation. Required.
+    :vartype text: str
+    :ivar offset_milliseconds: The start offset of the word in milliseconds. Required.
+    :vartype offset_milliseconds: int
+    :ivar duration_milliseconds: The duration of the word in milliseconds. Required.
+    :vartype duration_milliseconds: int
+    """
+
+    text: str = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The recognized word, including punctuation. Required."""
+    offset_milliseconds: int = rest_field(
+        name="offsetMilliseconds", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The start offset of the word in milliseconds. Required."""
+    duration_milliseconds: int = rest_field(
+        name="durationMilliseconds", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The duration of the word in milliseconds. Required."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        text: str,
+        offset_milliseconds: int,
+        duration_milliseconds: int,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class TranscriptionContent(_Model):
+    """Request model for transcription operation.
+
+    :ivar definition: Metadata for a transcription request. This field contains a JSON-serialized
+     object of type ``TranscriptionOptions``. Required.
+    :vartype definition: ~azure.ai.transcription.models.TranscriptionOptions
+    :ivar audio: The content of the audio file to be transcribed. The audio file must be shorter
+     than 2 hours in audio duration and smaller than 250 MB in size. Optional if audioUrl is
+     provided in the definition.
+    :vartype audio: ~azure.ai.transcription._utils.utils.FileType
+    """
+
+    definition: "_models.TranscriptionOptions" = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """Metadata for a transcription request. This field contains a JSON-serialized object of type
+     ``TranscriptionOptions``. Required."""
+    audio: Optional[FileType] = rest_field(
+        visibility=["read", "create", "update", "delete", "query"], is_multipart_file_input=True
+    )
+    """The content of the audio file to be transcribed. The audio file must be shorter than 2 hours in
+     audio duration and smaller than 250 MB in size. Optional if audioUrl is provided in the
+     definition."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        definition: "_models.TranscriptionOptions",
+        audio: Optional[FileType] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class TranscriptionDiarizationOptions(_Model):
+    """The Speaker Diarization settings. Diarization settings must be specified to enable speaker
+    diarization.
+
+    :ivar enabled: Enable speaker diarization. This is automatically set to true when maxSpeakers
+     is specified.
+    :vartype enabled: bool
+    :ivar max_speakers: Gets or sets a hint for the maximum number of speakers for diarization.
+     Must be greater than 1 and less than 36.
+    :vartype max_speakers: int
+    """
+
+    enabled: Optional[bool] = rest_field(visibility=["read"])
+    """Enable speaker diarization. This is automatically set to true when maxSpeakers is specified."""
+    max_speakers: Optional[int] = rest_field(
+        name="maxSpeakers", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Gets or sets a hint for the maximum number of speakers for diarization. Must be greater than 1
+     and less than 36."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        max_speakers: Optional[int] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class TranscriptionOptions(_Model):
+    """Metadata for a transcription request.
+
+    :ivar audio_url: The URL of the audio to be transcribed. The audio must be shorter than 2 hours
+     in audio duration and smaller than 250 MB in size. If both Audio and AudioUrl are provided,
+     Audio is used.
+    :vartype audio_url: str
+    :ivar locales: A list of possible locales for the transcription. If not specified, the locale
+     of the speech in the audio is detected automatically from all supported locales.
+    :vartype locales: list[str]
+    :ivar models: Maps some or all candidate locales to a model URI to be used for transcription.
+     If no mapping is given, the default model for the locale is used.
+    :vartype models: dict[str, str]
+    :ivar profanity_filter_mode: Mode of profanity filtering. Known values are: "None", "Removed",
+     "Tags", and "Masked".
+    :vartype profanity_filter_mode: str or ~azure.ai.transcription.models.ProfanityFilterMode
+    :ivar diarization_options: Mode of diarization.
+    :vartype diarization_options: ~azure.ai.transcription.models.TranscriptionDiarizationOptions
+    :ivar active_channels: The 0-based indices of the channels to be transcribed separately. If not
+     specified, multiple channels are merged and transcribed jointly. Only up to two channels are
+     supported.
+    :vartype active_channels: list[int]
+    :ivar enhanced_mode: Enhanced mode properties.
+    :vartype enhanced_mode: ~azure.ai.transcription.models.EnhancedModeProperties
+    :ivar phrase_list: Phrase list properties.
+    :vartype phrase_list: ~azure.ai.transcription.models.PhraseListProperties
+    """
+
+    audio_url: Optional[str] = rest_field(name="audioUrl", visibility=["read", "create", "update", "delete", "query"])
+    """The URL of the audio to be transcribed. The audio must be shorter than 2 hours in audio
+     duration and smaller than 250 MB in size. If both Audio and AudioUrl are provided, Audio is
+     used."""
+    locales: Optional[list[str]] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """A list of possible locales for the transcription. If not specified, the locale of the speech in
+     the audio is detected automatically from all supported locales."""
+    models: Optional[dict[str, str]] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """Maps some or all candidate locales to a model URI to be used for transcription. If no mapping
+     is given, the default model for the locale is used."""
+    profanity_filter_mode: Optional[Union[str, "_models.ProfanityFilterMode"]] = rest_field(
+        name="profanityFilterMode", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Mode of profanity filtering. Known values are: \"None\", \"Removed\", \"Tags\", and \"Masked\"."""
+    diarization_options: Optional["_models.TranscriptionDiarizationOptions"] = rest_field(
+        name="diarization", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Mode of diarization."""
+    active_channels: Optional[list[int]] = rest_field(
+        name="channels", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The 0-based indices of the channels to be transcribed separately. If not specified, multiple
+     channels are merged and transcribed jointly. Only up to two channels are supported."""
+    enhanced_mode: Optional["_models.EnhancedModeProperties"] = rest_field(
+        name="enhancedMode", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Enhanced mode properties."""
+    phrase_list: Optional["_models.PhraseListProperties"] = rest_field(
+        name="phraseList", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """Phrase list properties."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        audio_url: Optional[str] = None,
+        locales: Optional[list[str]] = None,
+        models: Optional[dict[str, str]] = None,
+        profanity_filter_mode: Optional[Union[str, "_models.ProfanityFilterMode"]] = None,
+        diarization_options: Optional["_models.TranscriptionDiarizationOptions"] = None,
+        active_channels: Optional[list[int]] = None,
+        enhanced_mode: Optional["_models.EnhancedModeProperties"] = None,
+        phrase_list: Optional["_models.PhraseListProperties"] = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+
+
+class TranscriptionResult(_Model):
+    """The result of the transcribe operation.
+
+    :ivar duration_milliseconds: The duration of the audio in milliseconds. Required.
+    :vartype duration_milliseconds: int
+    :ivar combined_phrases: The full transcript for each channel. Required.
+    :vartype combined_phrases: list[~azure.ai.transcription.models.ChannelCombinedPhrases]
+    :ivar phrases: The transcription results segmented into phrases. Required.
+    :vartype phrases: list[~azure.ai.transcription.models.TranscribedPhrase]
+    """
+
+    duration_milliseconds: int = rest_field(
+        name="durationMilliseconds", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The duration of the audio in milliseconds. Required."""
+    combined_phrases: list["_models.ChannelCombinedPhrases"] = rest_field(
+        name="combinedPhrases", visibility=["read", "create", "update", "delete", "query"]
+    )
+    """The full transcript for each channel. Required."""
+    phrases: list["_models.TranscribedPhrase"] = rest_field(visibility=["read", "create", "update", "delete", "query"])
+    """The transcription results segmented into phrases. Required."""
+
+    @overload
+    def __init__(
+        self,
+        *,
+        duration_milliseconds: int,
+        combined_phrases: list["_models.ChannelCombinedPhrases"],
+        phrases: list["_models.TranscribedPhrase"],
+    ) -> None: ...
+
+    @overload
+    def __init__(self, mapping: Mapping[str, Any]) -> None:
+        """
+        :param mapping: raw JSON to initialize the model.
+        :type mapping: Mapping[str, Any]
+        """
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)

azure/ai/transcription/models/_patch.py

@@ -0,0 +1,21 @@
+# coding=utf-8
+# --------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License. See License.txt in the project root for license information.
+# --------------------------------------------------------------------------
+"""Customize generated code here.
+
+Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize
+"""
+
+
+__all__: list[str] = []  # Add all objects you want publicly available to users at this package level
+
+
+def patch_sdk():
+    """Do not remove from this file.
+
+    `patch_sdk` is a last resort escape hatch that allows you to do customizations
+    you can't accomplish using the techniques described in
+    https://aka.ms/azsdk/python/dpcodegen/python/customize
+    """

azure/ai/transcription/py.typed

@@ -0,0 +1 @@
+# Marker file for PEP 561.