sarvamai 0.1.11a5__tar.gz → 0.1.11a6__tar.gz

{sarvamai-0.1.11a5 → sarvamai-0.1.11a6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.11a5
+Version: 0.1.11a6
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.11a5 → sarvamai-0.1.11a6}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.11a5"
+version = "0.1.11a6"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.11a5 → 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/0.1.11a5",
+            "User-Agent": "sarvamai/0.1.11a6",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.11a5",
+            "X-Fern-SDK-Version": "0.1.11a6",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

{sarvamai-0.1.11a5 → 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
 
@@ -234,11 +236,11 @@ class SpeechToTextJobClient:
 
     def create_job(
         self,
-        language_code: typing.Optional[str] = None,
-        model: typing.Optional[str] = "saarika:v2.5",
+        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,
-        with_diarization: typing.Optional[bool] = False,
-        with_timestamps: typing.Optional[bool] = False,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextJob:
@@ -247,21 +249,21 @@ class SpeechToTextJobClient:
 
         Parameters
         ----------
-        language_code : typing.Optional[str], default=None
-            The language code of the input audio (e.g., "en", "hi").
-
-        model : typing.Optional[str], default="saarika:v2.5"
+        model : SpeechToTextModel, default="saarika:v2.5"
             The model to use for transcription.
 
-        num_speakers : typing.Optional[int], default=None
-            The number of distinct speakers in the audio, if known.
-
         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.
 
@@ -278,8 +280,8 @@ class SpeechToTextJobClient:
                 language_code=language_code,
                 model=model,
                 num_speakers=num_speakers,  # type: ignore[typeddict-item]
-                with_diarization=with_diarization,  # type: ignore[typeddict-item]
-                with_timestamps=with_timestamps,  # type: ignore[typeddict-item]
+                with_diarization=with_diarization,
+                with_timestamps=with_timestamps,
             ),
             callback=callback,
             request_options=request_options,
@@ -562,11 +564,11 @@ class AsyncSpeechToTextJobClient:
 
     async def create_job(
         self,
-        language_code: typing.Optional[str] = None,
-        model: typing.Optional[str] = "saarika:v2.5",
+        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,
-        with_diarization: typing.Optional[bool] = False,
-        with_timestamps: typing.Optional[bool] = False,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> "AsyncSpeechToTextJob":
@@ -575,21 +577,21 @@ class AsyncSpeechToTextJobClient:
 
         Parameters
         ----------
-        language_code : typing.Optional[str], default=None
-            The language code of the input audio (e.g., "en", "hi").
-
-        model : typing.Optional[str], default="saarika:v2.5"
+        model : SpeechToTextModel, default="saarika:v2.5"
             The model to use for transcription.
 
-        num_speakers : typing.Optional[int], default=None
-            The number of distinct speakers in the audio, if known.
-
         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.
 
@@ -605,9 +607,9 @@ class AsyncSpeechToTextJobClient:
             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]
-                with_diarization=with_diarization,  # type: ignore[typeddict-item]
-                with_timestamps=with_timestamps,  # type: ignore[typeddict-item]
             ),
             callback=callback,
             request_options=request_options,

{sarvamai-0.1.11a5 → sarvamai-0.1.11a6}/src/sarvamai/speech_to_text_translate_job/client.py

@@ -12,6 +12,7 @@ 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,
@@ -251,10 +252,10 @@ class SpeechToTextTranslateJobClient:
 
     def create_job(
         self,
+        model: SpeechToTextTranslateModel = "saaras:v2.5",
+        with_diarization: bool = False,
         prompt: typing.Optional[str] = None,
-        model: typing.Optional[str] = "saaras:v2.5",
         num_speakers: typing.Optional[int] = None,
-        with_diarization: typing.Optional[bool] = False,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextTranslateJob:
@@ -263,18 +264,18 @@ class SpeechToTextTranslateJobClient:
 
         Parameters
         ----------
+        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.
 
-        model : typing.Optional[str], default="saaras:v2.5"
-            The model to use for speech-to-text translation.
-
         num_speakers : typing.Optional[int], default=None
             The number of distinct speakers in the input audio, if known.
 
-        with_diarization : typing.Optional[bool], default=False
-            Whether to enable speaker diarization (i.e., distinguishing who is speaking).
-
         callback : typing.Optional[BulkJobCallbackParams], default=OMIT
             Optional callback configuration to receive job completion events via webhook.
 
@@ -290,7 +291,7 @@ class SpeechToTextTranslateJobClient:
             job_parameters=SpeechToTextTranslateJobParametersParams(
                 prompt=prompt,  # type: ignore[typeddict-item]
                 model=model,
-                with_diarization=with_diarization,  # type: ignore[typeddict-item]
+                with_diarization=with_diarization,
                 num_speakers=num_speakers,  # type: ignore[typeddict-item]
             ),
             callback=callback,
@@ -586,10 +587,10 @@ class AsyncSpeechToTextTranslateJobClient:
 
     async def create_job(
         self,
+        model: SpeechToTextTranslateModel = "saaras:v2.5",
+        with_diarization: bool = False,
         prompt: typing.Optional[str] = None,
-        model: typing.Optional[str] = "saaras:v2.5",
         num_speakers: typing.Optional[int] = None,
-        with_diarization: typing.Optional[bool] = False,
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> "AsyncSpeechToTextTranslateJob":
@@ -598,18 +599,18 @@ class AsyncSpeechToTextTranslateJobClient:
 
         Parameters
         ----------
+        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.
 
-        model : typing.Optional[str], default="saaras:v2.5"
-            The model to use for speech-to-text translation.
-
         num_speakers : typing.Optional[int], default=None
             The number of distinct speakers in the input audio, if known.
 
-        with_diarization : typing.Optional[bool], default=False
-            Whether to enable speaker diarization (i.e., distinguishing who is speaking).
-
         callback : typing.Optional[BulkJobCallbackParams], default=OMIT
             Optional callback configuration to receive job completion events via webhook.