sarvamai 0.1.5a5__py3-none-any.whl → 0.1.5a6__py3-none-any.whl

sarvamai/speech_to_text_streaming/raw_client.py

@@ -1,166 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-from contextlib import asynccontextmanager, contextmanager
-
-import httpx
-import websockets
-import websockets.sync.client as websockets_sync_client
-from ..core.api_error import ApiError
-from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
-from ..core.request_options import RequestOptions
-from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
-from .types.speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .types.speech_to_text_streaming_model import SpeechToTextStreamingModel
-
-
-class RawSpeechToTextStreamingClient:
-    def __init__(self, *, client_wrapper: SyncClientWrapper):
-        self._client_wrapper = client_wrapper
-
-    @contextmanager
-    def connect(
-        self,
-        *,
-        language_code: SpeechToTextStreamingLanguageCode,
-        model: SpeechToTextStreamingModel,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
-        api_subscription_key: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> typing.Iterator[SpeechToTextStreamingSocketClient]:
-        """
-        WebSocket channel for real-time speech to text streaming
-
-        Parameters
-        ----------
-        language_code : SpeechToTextStreamingLanguageCode
-            Language code for speech recognition
-
-        model : SpeechToTextStreamingModel
-            Speech to text model to use
-
-        high_vad_sensitivity : typing.Optional[str]
-            Enable high VAD (Voice Activity Detection) sensitivity
-
-        vad_signals : typing.Optional[str]
-            Enable VAD signals in response
-
-        api_subscription_key : typing.Optional[str]
-            API subscription key for authentication
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        SpeechToTextStreamingSocketClient
-        """
-        ws_url = self._client_wrapper.get_environment().production + "/speech-to-text/ws"
-        query_params = httpx.QueryParams()
-        if language_code is not None:
-            query_params = query_params.add("language-code", language_code)
-        if model is not None:
-            query_params = query_params.add("model", model)
-        if high_vad_sensitivity is not None:
-            query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
-        if vad_signals is not None:
-            query_params = query_params.add("vad_signals", vad_signals)
-        ws_url = ws_url + f"?{query_params}"
-        headers = self._client_wrapper.get_headers()
-        if api_subscription_key is not None:
-            headers["Api-Subscription-Key"] = str(api_subscription_key)
-        if request_options and "additional_headers" in request_options:
-            headers.update(request_options["additional_headers"])
-        try:
-            with websockets_sync_client.connect(ws_url, additional_headers=headers) as protocol:
-                yield SpeechToTextStreamingSocketClient(websocket=protocol)
-        except websockets.exceptions.InvalidStatusCode as exc:
-            status_code: int = exc.status_code
-            if status_code == 401:
-                raise ApiError(
-                    status_code=status_code,
-                    headers=dict(headers),
-                    body="Websocket initialized with invalid credentials.",
-                )
-            raise ApiError(
-                status_code=status_code,
-                headers=dict(headers),
-                body="Unexpected error when initializing websocket connection.",
-            )
-
-
-class AsyncRawSpeechToTextStreamingClient:
-    def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._client_wrapper = client_wrapper
-
-    @asynccontextmanager
-    async def connect(
-        self,
-        *,
-        language_code: SpeechToTextStreamingLanguageCode,
-        model: SpeechToTextStreamingModel,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
-        api_subscription_key: typing.Optional[str] = None,
-        request_options: typing.Optional[RequestOptions] = None,
-    ) -> typing.AsyncIterator[AsyncSpeechToTextStreamingSocketClient]:
-        """
-        WebSocket channel for real-time speech to text streaming
-
-        Parameters
-        ----------
-        language_code : SpeechToTextStreamingLanguageCode
-            Language code for speech recognition
-
-        model : SpeechToTextStreamingModel
-            Speech to text model to use
-
-        high_vad_sensitivity : typing.Optional[str]
-            Enable high VAD (Voice Activity Detection) sensitivity
-
-        vad_signals : typing.Optional[str]
-            Enable VAD signals in response
-
-        api_subscription_key : typing.Optional[str]
-            API subscription key for authentication
-
-        request_options : typing.Optional[RequestOptions]
-            Request-specific configuration.
-
-        Returns
-        -------
-        AsyncSpeechToTextStreamingSocketClient
-        """
-        ws_url = self._client_wrapper.get_environment().production + "/speech-to-text/ws"
-        query_params = httpx.QueryParams()
-        if language_code is not None:
-            query_params = query_params.add("language-code", language_code)
-        if model is not None:
-            query_params = query_params.add("model", model)
-        if high_vad_sensitivity is not None:
-            query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
-        if vad_signals is not None:
-            query_params = query_params.add("vad_signals", vad_signals)
-        ws_url = ws_url + f"?{query_params}"
-        headers = self._client_wrapper.get_headers()
-        if api_subscription_key is not None:
-            headers["Api-Subscription-Key"] = str(api_subscription_key)
-        if request_options and "additional_headers" in request_options:
-            headers.update(request_options["additional_headers"])
-        try:
-            async with websockets.connect(ws_url, extra_headers=headers) as protocol:
-                yield AsyncSpeechToTextStreamingSocketClient(websocket=protocol)
-        except websockets.exceptions.InvalidStatusCode as exc:
-            status_code: int = exc.status_code
-            if status_code == 401:
-                raise ApiError(
-                    status_code=status_code,
-                    headers=dict(headers),
-                    body="Websocket initialized with invalid credentials.",
-                )
-            raise ApiError(
-                status_code=status_code,
-                headers=dict(headers),
-                body="Unexpected error when initializing websocket connection.",
-            )

sarvamai/speech_to_text_streaming/socket_client.py

@@ -1,129 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import json
-import typing
-
-import websockets
-import websockets.sync.connection as websockets_sync_connection
-from ..core.events import EventEmitterMixin, EventType
-from ..core.pydantic_utilities import parse_obj_as
-from ..types.audio_message import AudioMessage
-from ..types.speech_to_text_streaming_response import SpeechToTextStreamingResponse
-
-SpeechToTextStreamingSocketClientResponse = typing.Union[SpeechToTextStreamingResponse]
-
-
-class AsyncSpeechToTextStreamingSocketClient(EventEmitterMixin):
-    def __init__(self, *, websocket: websockets.WebSocketClientProtocol):
-        super().__init__()
-        self._websocket = websocket
-
-    async def __aiter__(self):
-        async for message in self._websocket:
-            yield parse_obj_as(SpeechToTextStreamingSocketClientResponse, message)  # type: ignore
-
-    async def start_listening(self):
-        """
-        Start listening for messages on the websocket connection.
-
-        Emits events in the following order:
-        - EventType.OPEN when connection is established
-        - EventType.MESSAGE for each message received
-        - EventType.ERROR if an error occurs
-        - EventType.CLOSE when connection is closed
-        """
-        self._emit(EventType.OPEN, None)
-        try:
-            async for raw_message in self._websocket:
-                parsed = parse_obj_as(SpeechToTextStreamingSocketClientResponse, raw_message)  # type: ignore
-                self._emit(EventType.MESSAGE, parsed)
-        except websockets.WebSocketException as exc:
-            self._emit(EventType.ERROR, exc)
-        finally:
-            self._emit(EventType.CLOSE, None)
-
-    async def send_audio_message(self, message: AudioMessage) -> None:
-        """
-        Send a message to the websocket connection.
-        The message will be sent as a AudioMessage.
-        """
-        await self._send_model(message)
-
-    async def recv(self) -> SpeechToTextStreamingSocketClientResponse:
-        """
-        Receive a message from the websocket connection.
-        """
-        data = await self._websocket.recv()
-        return parse_obj_as(SpeechToTextStreamingSocketClientResponse, data)  # type: ignore
-
-    async def _send(self, data: typing.Any) -> None:
-        """
-        Send a message to the websocket connection.
-        """
-        if isinstance(data, dict):
-            data = json.dumps(data)
-        await self._websocket.send(data)
-
-    async def _send_model(self, data: typing.Any) -> None:
-        """
-        Send a Pydantic model to the websocket connection.
-        """
-        await self._send(data.dict())
-
-
-class SpeechToTextStreamingSocketClient(EventEmitterMixin):
-    def __init__(self, *, websocket: websockets_sync_connection.Connection):
-        super().__init__()
-        self._websocket = websocket
-
-    def __iter__(self):
-        for message in self._websocket:
-            yield parse_obj_as(SpeechToTextStreamingSocketClientResponse, message)  # type: ignore
-
-    def start_listening(self):
-        """
-        Start listening for messages on the websocket connection.
-
-        Emits events in the following order:
-        - EventType.OPEN when connection is established
-        - EventType.MESSAGE for each message received
-        - EventType.ERROR if an error occurs
-        - EventType.CLOSE when connection is closed
-        """
-        self._emit(EventType.OPEN, None)
-        try:
-            for raw_message in self._websocket:
-                parsed = parse_obj_as(SpeechToTextStreamingSocketClientResponse, raw_message)  # type: ignore
-                self._emit(EventType.MESSAGE, parsed)
-        except websockets.WebSocketException as exc:
-            self._emit(EventType.ERROR, exc)
-        finally:
-            self._emit(EventType.CLOSE, None)
-
-    def send_audio_message(self, message: AudioMessage) -> None:
-        """
-        Send a message to the websocket connection.
-        The message will be sent as a AudioMessage.
-        """
-        self._send_model(message)
-
-    def recv(self) -> SpeechToTextStreamingSocketClientResponse:
-        """
-        Receive a message from the websocket connection.
-        """
-        data = self._websocket.recv()
-        return parse_obj_as(SpeechToTextStreamingSocketClientResponse, data)  # type: ignore
-
-    def _send(self, data: typing.Any) -> None:
-        """
-        Send a message to the websocket connection.
-        """
-        if isinstance(data, dict):
-            data = json.dumps(data)
-        self._websocket.send(data)
-
-    def _send_model(self, data: typing.Any) -> None:
-        """
-        Send a Pydantic model to the websocket connection.
-        """
-        self._send(data.dict())

sarvamai/speech_to_text_streaming/types/__init__.py

@@ -1,8 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-# isort: skip_file
-
-from .speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .speech_to_text_streaming_model import SpeechToTextStreamingModel
-
-__all__ = ["SpeechToTextStreamingLanguageCode", "SpeechToTextStreamingModel"]

sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_language_code.py

@@ -1,8 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-SpeechToTextStreamingLanguageCode = typing.Union[
-    typing.Literal["en-IN", "hi-IN", "bn-IN", "gu-IN", "kn-IN", "ml-IN", "mr-IN", "od-IN", "pa-IN", "ta-IN", "te-IN"],
-    typing.Any,
-]

sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_model.py

@@ -1,5 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-SpeechToTextStreamingModel = typing.Union[typing.Literal["saarika:v2.5", "saarika:v2"], typing.Any]

sarvamai/types/audio_data.py

@@ -1,33 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .audio_data_encoding import AudioDataEncoding
-
-
-class AudioData(UniversalBaseModel):
-    data: str = pydantic.Field()
-    """
-    Base64 encoded audio data
-    """
-
-    sample_rate: int = pydantic.Field()
-    """
-    Audio sample rate in Hz (16kHz preferred, 8kHz least preferred)
-    """
-
-    encoding: AudioDataEncoding = pydantic.Field()
-    """
-    Audio encoding format
-    """
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai/types/audio_data_encoding.py

@@ -1,5 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-AudioDataEncoding = typing.Union[typing.Literal["audio/wav", "audio/pcm", "audio/flac", "audio/mp3"], typing.Any]

sarvamai/types/audio_message.py

@@ -1,20 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .audio_data import AudioData
-
-
-class AudioMessage(UniversalBaseModel):
-    audio: AudioData
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai/types/error_data.py

@@ -1,27 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-
-
-class ErrorData(UniversalBaseModel):
-    error: str = pydantic.Field()
-    """
-    Error message
-    """
-
-    code: str = pydantic.Field()
-    """
-    Error code
-    """
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai/types/events_data.py

@@ -1,28 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-
-
-class EventsData(UniversalBaseModel):
-    event_type: str = pydantic.Field()
-    """
-    Type of event
-    """
-
-    timestamp: dt.datetime = pydantic.Field()
-    """
-    Event timestamp
-    """
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai/types/format.py

@@ -1,5 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-Format = typing.Union[typing.Literal["wav", "mp3"], typing.Any]

sarvamai/types/speech_to_text_streaming_response.py

@@ -1,22 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .speech_to_text_streaming_response_data import SpeechToTextStreamingResponseData
-from .speech_to_text_streaming_response_type import SpeechToTextStreamingResponseType
-
-
-class SpeechToTextStreamingResponse(UniversalBaseModel):
-    type: SpeechToTextStreamingResponseType
-    data: SpeechToTextStreamingResponseData
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai/types/speech_to_text_streaming_response_data.py

@@ -1,9 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-from .error_data import ErrorData
-from .events_data import EventsData
-from .transcription_data import TranscriptionData
-
-SpeechToTextStreamingResponseData = typing.Union[TranscriptionData, ErrorData, EventsData]

sarvamai/types/speech_to_text_streaming_response_type.py

@@ -1,5 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-SpeechToTextStreamingResponseType = typing.Union[typing.Literal["data", "error", "events"], typing.Any]

sarvamai/types/transcription_data.py

@@ -1,45 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .transcription_metrics import TranscriptionMetrics
-
-
-class TranscriptionData(UniversalBaseModel):
-    request_id: str = pydantic.Field()
-    """
-    Unique identifier for the request
-    """
-
-    transcript: str = pydantic.Field()
-    """
-    Transcript of the provided speech
-    """
-
-    timestamps: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = pydantic.Field(default=None)
-    """
-    Timestamp information (if available)
-    """
-
-    diarized_transcript: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = pydantic.Field(default=None)
-    """
-    Diarized transcript of the provided speech
-    """
-
-    language_code: typing.Optional[str] = pydantic.Field(default=None)
-    """
-    BCP-47 code of detected language
-    """
-
-    metrics: TranscriptionMetrics
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai/types/transcription_metrics.py

@@ -1,27 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-
-
-class TranscriptionMetrics(UniversalBaseModel):
-    audio_duration: float = pydantic.Field()
-    """
-    Duration of processed audio in seconds
-    """
-
-    processing_latency: float = pydantic.Field()
-    """
-    Processing latency in seconds
-    """
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai-0.1.5a5.dist-info/METADATA

@@ -1,28 +0,0 @@
-Metadata-Version: 2.1
-Name: sarvamai
-Version: 0.1.5a5
-Summary: 
-Requires-Python: >=3.8,<4.0
-Classifier: Intended Audience :: Developers
-Classifier: Operating System :: MacOS
-Classifier: Operating System :: Microsoft :: Windows
-Classifier: Operating System :: OS Independent
-Classifier: Operating System :: POSIX
-Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Typing :: Typed
-Requires-Dist: httpx (>=0.21.2)
-Requires-Dist: pydantic (>=1.9.2)
-Requires-Dist: pydantic-core (>=2.18.2,<3.0.0)
-Requires-Dist: typing_extensions (>=4.0.0)
-Requires-Dist: websockets (==12.0)
-Description-Content-Type: text/markdown
-
-