sarvamai 0.1.11a4__tar.gz → 0.1.11a6__tar.gz

{sarvamai-0.1.11a4 → sarvamai-0.1.11a6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.11a4
+Version: 0.1.11a6
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.11a4 → sarvamai-0.1.11a6}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.11a4"
+version = "0.1.11a6"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.11a4 → sarvamai-0.1.11a6}/src/sarvamai/core/client_wrapper.py

@@ -23,10 +23,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.11a4",
+            "User-Agent": "sarvamai/0.1.11a6",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.11a4",
+            "X-Fern-SDK-Version": "0.1.11a6",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

{sarvamai-0.1.11a4 → sarvamai-0.1.11a6}/src/sarvamai/speech_to_text_job/client.py

@@ -10,6 +10,8 @@ from ..types.bulk_job_init_response_v_1 import BulkJobInitResponseV1
 from ..types.files_download_response import FilesDownloadResponse
 from ..types.files_upload_response import FilesUploadResponse
 from ..types.job_status_v_1 import JobStatusV1
+from ..types.speech_to_text_model import SpeechToTextModel
+from ..types.speech_to_text_language import SpeechToTextLanguage
 from .raw_client import AsyncRawSpeechToTextJobClient, RawSpeechToTextJobClient
 from .job import AsyncSpeechToTextJob, SpeechToTextJob
 
@@ -234,7 +236,11 @@ class SpeechToTextJobClient:
 
     def create_job(
         self,
-        job_parameters: SpeechToTextJobParametersParams,
+        model: SpeechToTextModel = "saarika:v2.5",
+        with_diarization: bool = False,
+        with_timestamps: bool = False,
+        language_code: typing.Optional[SpeechToTextLanguage] = None,
+        num_speakers: typing.Optional[int] = None,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextJob:
@@ -243,8 +249,20 @@ class SpeechToTextJobClient:
 
         Parameters
         ----------
-        job_parameters : SpeechToTextJobParametersParams
-            The parameters required to configure the speech-to-text job.
+        model : SpeechToTextModel, default="saarika:v2.5"
+            The model to use for transcription.
+
+        with_diarization : typing.Optional[bool], default=False
+            Whether to enable speaker diarization (distinguishing who said what).
+
+        with_timestamps : typing.Optional[bool], default=False
+            Whether to include word-level timestamps in the transcription output.
+
+        language_code : typing.Optional[SpeechToTextLanguage], default=None
+            The language code of the input audio (e.g., "hi-IN", "bn-IN").
+            
+        num_speakers : typing.Optional[int], default=None
+            The number of distinct speakers in the audio, if known.
 
         callback : typing.Optional[BulkJobCallbackParams], default=OMIT
             Optional callback configuration to receive job completion events.
@@ -258,7 +276,13 @@ class SpeechToTextJobClient:
             A handle to the newly created Speech-to-Text job.
         """
         response = self.initialise(
-            job_parameters=job_parameters,
+            job_parameters=SpeechToTextJobParametersParams(
+                language_code=language_code,
+                model=model,
+                num_speakers=num_speakers,  # type: ignore[typeddict-item]
+                with_diarization=with_diarization,
+                with_timestamps=with_timestamps,
+            ),
             callback=callback,
             request_options=request_options,
         )
@@ -540,7 +564,11 @@ class AsyncSpeechToTextJobClient:
 
     async def create_job(
         self,
-        job_parameters: SpeechToTextJobParametersParams,
+        model: SpeechToTextModel = "saarika:v2.5",
+        with_diarization: bool = False,
+        with_timestamps: bool = False,
+        language_code: typing.Optional[SpeechToTextLanguage] = None,
+        num_speakers: typing.Optional[int] = None,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> "AsyncSpeechToTextJob":
@@ -549,8 +577,20 @@ class AsyncSpeechToTextJobClient:
 
         Parameters
         ----------
-        job_parameters : SpeechToTextJobParametersParams
-            The parameters required to configure the speech-to-text  job.
+        model : SpeechToTextModel, default="saarika:v2.5"
+            The model to use for transcription.
+
+        with_diarization : typing.Optional[bool], default=False
+            Whether to enable speaker diarization (distinguishing who said what).
+
+        with_timestamps : typing.Optional[bool], default=False
+            Whether to include word-level timestamps in the transcription output.
+
+        language_code : typing.Optional[SpeechToTextLanguage], default=None
+            The language code of the input audio (e.g., "hi-IN", "bn-IN").
+            
+        num_speakers : typing.Optional[int], default=None
+            The number of distinct speakers in the audio, if known.
 
         callback : typing.Optional[BulkJobCallbackParams], default=OMIT
             Optional callback configuration to receive job completion events.
@@ -564,7 +604,13 @@ class AsyncSpeechToTextJobClient:
             A handle to the newly created job.
         """
         response = await self.initialise(
-            job_parameters=job_parameters,
+            job_parameters=SpeechToTextJobParametersParams(
+                language_code=language_code,
+                model=model,
+                with_diarization=with_diarization,
+                with_timestamps=with_timestamps,
+                num_speakers=num_speakers,  # type: ignore[typeddict-item]
+            ),
             callback=callback,
             request_options=request_options,
         )

{sarvamai-0.1.11a4 → sarvamai-0.1.11a6}/src/sarvamai/speech_to_text_translate_job/client.py

@@ -5,13 +5,19 @@ import typing
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from ..requests.bulk_job_callback import BulkJobCallbackParams
-from ..requests.speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParametersParams
+from ..requests.speech_to_text_translate_job_parameters import (
+    SpeechToTextTranslateJobParametersParams,
+)
 from ..types.bulk_job_init_response_v_1 import BulkJobInitResponseV1
 from ..types.files_download_response import FilesDownloadResponse
 from ..types.files_upload_response import FilesUploadResponse
 from ..types.job_status_v_1 import JobStatusV1
+from ..types.speech_to_text_translate_model import SpeechToTextTranslateModel
 from .job import AsyncSpeechToTextTranslateJob, SpeechToTextTranslateJob
-from .raw_client import AsyncRawSpeechToTextTranslateJobClient, RawSpeechToTextTranslateJobClient
+from .raw_client import (
+    AsyncRawSpeechToTextTranslateJobClient,
+    RawSpeechToTextTranslateJobClient,
+)
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -19,7 +25,9 @@ OMIT = typing.cast(typing.Any, ...)
 
 class SpeechToTextTranslateJobClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
-        self._raw_client = RawSpeechToTextTranslateJobClient(client_wrapper=client_wrapper)
+        self._raw_client = RawSpeechToTextTranslateJobClient(
+            client_wrapper=client_wrapper
+        )
 
     @property
     def with_raw_response(self) -> RawSpeechToTextTranslateJobClient:
@@ -73,11 +81,16 @@ class SpeechToTextTranslateJobClient:
         )
         """
         _response = self._raw_client.initialise(
-            job_parameters=job_parameters, ptu_id=ptu_id, callback=callback, request_options=request_options
+            job_parameters=job_parameters,
+            ptu_id=ptu_id,
+            callback=callback,
+            request_options=request_options,
         )
         return _response.data
 
-    def get_status(self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None) -> JobStatusV1:
+    def get_status(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> JobStatusV1:
         """
         Get the status of a speech to text translate bulk job V1
 
@@ -144,7 +157,9 @@ class SpeechToTextTranslateJobClient:
             job_id="job_id",
         )
         """
-        _response = self._raw_client.start(job_id, ptu_id=ptu_id, request_options=request_options)
+        _response = self._raw_client.start(
+            job_id, ptu_id=ptu_id, request_options=request_options
+        )
         return _response.data
 
     def get_upload_links(
@@ -237,7 +252,10 @@ class SpeechToTextTranslateJobClient:
 
     def create_job(
         self,
-        job_parameters: SpeechToTextTranslateJobParametersParams,
+        model: SpeechToTextTranslateModel = "saaras:v2.5",
+        with_diarization: bool = False,
+        prompt: typing.Optional[str] = None,
+        num_speakers: typing.Optional[int] = None,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextTranslateJob:
@@ -246,14 +264,23 @@ class SpeechToTextTranslateJobClient:
 
         Parameters
         ----------
-        job_parameters : SpeechToTextTranslateJobParametersParams
-            The parameters required to configure the speech-to-text-translate job.
+        model : typing.Optional[SpeechToTextTranslateModel], default="saaras:v2.5"
+            The model to use for speech-to-text translation.
+
+        with_diarization : typing.Optional[bool], default=False
+            Whether to enable speaker diarization (i.e., distinguishing who is speaking).
+
+        prompt : typing.Optional[str], default=None
+            An optional prompt to guide the transcription and translation model.
+
+        num_speakers : typing.Optional[int], default=None
+            The number of distinct speakers in the input audio, if known.
 
         callback : typing.Optional[BulkJobCallbackParams], default=OMIT
-            Optional callback configuration to receive job completion events.
+            Optional callback configuration to receive job completion events via webhook.
 
         request_options : typing.Optional[RequestOptions], default=None
-            Request-specific configuration.
+            Optional configuration for request timeout, retries, etc.
 
         Returns
         -------
@@ -261,7 +288,12 @@ class SpeechToTextTranslateJobClient:
             A handle to the newly created Speech-to-Text-Translate job.
         """
         response = self.initialise(
-            job_parameters=job_parameters,
+            job_parameters=SpeechToTextTranslateJobParametersParams(
+                prompt=prompt,  # type: ignore[typeddict-item]
+                model=model,
+                with_diarization=with_diarization,
+                num_speakers=num_speakers,  # type: ignore[typeddict-item]
+            ),
             callback=callback,
             request_options=request_options,
         )
@@ -286,7 +318,9 @@ class SpeechToTextTranslateJobClient:
 
 class AsyncSpeechToTextTranslateJobClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._raw_client = AsyncRawSpeechToTextTranslateJobClient(client_wrapper=client_wrapper)
+        self._raw_client = AsyncRawSpeechToTextTranslateJobClient(
+            client_wrapper=client_wrapper
+        )
 
     @property
     def with_raw_response(self) -> AsyncRawSpeechToTextTranslateJobClient:
@@ -348,11 +382,16 @@ class AsyncSpeechToTextTranslateJobClient:
         asyncio.run(main())
         """
         _response = await self._raw_client.initialise(
-            job_parameters=job_parameters, ptu_id=ptu_id, callback=callback, request_options=request_options
+            job_parameters=job_parameters,
+            ptu_id=ptu_id,
+            callback=callback,
+            request_options=request_options,
         )
         return _response.data
 
-    async def get_status(self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None) -> JobStatusV1:
+    async def get_status(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> JobStatusV1:
         """
         Get the status of a speech to text translate bulk job V1
 
@@ -388,7 +427,9 @@ class AsyncSpeechToTextTranslateJobClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.get_status(job_id, request_options=request_options)
+        _response = await self._raw_client.get_status(
+            job_id, request_options=request_options
+        )
         return _response.data
 
     async def start(
@@ -435,7 +476,9 @@ class AsyncSpeechToTextTranslateJobClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.start(job_id, ptu_id=ptu_id, request_options=request_options)
+        _response = await self._raw_client.start(
+            job_id, ptu_id=ptu_id, request_options=request_options
+        )
         return _response.data
 
     async def get_upload_links(
@@ -544,7 +587,10 @@ class AsyncSpeechToTextTranslateJobClient:
 
     async def create_job(
         self,
-        job_parameters: SpeechToTextTranslateJobParametersParams,
+        model: SpeechToTextTranslateModel = "saaras:v2.5",
+        with_diarization: bool = False,
+        prompt: typing.Optional[str] = None,
+        num_speakers: typing.Optional[int] = None,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> "AsyncSpeechToTextTranslateJob":
@@ -553,14 +599,23 @@ class AsyncSpeechToTextTranslateJobClient:
 
         Parameters
         ----------
-        job_parameters : SpeechToTextTranslateJobParametersParams
-            The parameters required to configure the speech-to-text translate job.
+        model : typing.Optional[SpeechToTextTranslateModel], default="saaras:v2.5"
+            The model to use for speech-to-text translation.
+        
+        with_diarization : typing.Optional[bool], default=False
+            Whether to enable speaker diarization (i.e., distinguishing who is speaking).
+
+        prompt : typing.Optional[str], default=None
+            An optional prompt to guide the transcription and translation model.
+
+        num_speakers : typing.Optional[int], default=None
+            The number of distinct speakers in the input audio, if known.
 
         callback : typing.Optional[BulkJobCallbackParams], default=OMIT
-            Optional callback configuration to receive job completion events.
+            Optional callback configuration to receive job completion events via webhook.
 
         request_options : typing.Optional[RequestOptions], default=None
-            Request-specific configuration.
+            Optional configuration for request timeout, retries, etc.
 
         Returns
         -------
@@ -568,7 +623,12 @@ class AsyncSpeechToTextTranslateJobClient:
             A handle to the newly created job.
         """
         response = await self.initialise(
-            job_parameters=job_parameters,
+            job_parameters=SpeechToTextTranslateJobParametersParams(
+                prompt=prompt,  # type: ignore[typeddict-item]
+                model=model,
+                with_diarization=with_diarization,  # type: ignore[typeddict-item]
+                num_speakers=num_speakers,  # type: ignore[typeddict-item]
+            ),
             callback=callback,
             request_options=request_options,
         )