sarvamai 0.1.22a3__py3-none-any.whl → 0.1.23a1__py3-none-any.whl

sarvamai/speech_to_text_translate_streaming/__init__.py

@@ -2,18 +2,45 @@
 
 # isort: skip_file
 
-from .types import (
-    SpeechToTextTranslateStreamingFlushSignal,
-    SpeechToTextTranslateStreamingHighVadSensitivity,
-    SpeechToTextTranslateStreamingInputAudioCodec,
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-    SpeechToTextTranslateStreamingVadSignals,
-)
+import typing
+from importlib import import_module
+
+if typing.TYPE_CHECKING:
+    from .types import (
+        SpeechToTextTranslateStreamingFlushSignal,
+        SpeechToTextTranslateStreamingHighVadSensitivity,
+        SpeechToTextTranslateStreamingVadSignals,
+    )
+_dynamic_imports: typing.Dict[str, str] = {
+    "SpeechToTextTranslateStreamingFlushSignal": ".types",
+    "SpeechToTextTranslateStreamingHighVadSensitivity": ".types",
+    "SpeechToTextTranslateStreamingVadSignals": ".types",
+}
+
+
+def __getattr__(attr_name: str) -> typing.Any:
+    module_name = _dynamic_imports.get(attr_name)
+    if module_name is None:
+        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
+    try:
+        module = import_module(module_name, __package__)
+        if module_name == f".{attr_name}":
+            return module
+        else:
+            return getattr(module, attr_name)
+    except ImportError as e:
+        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
+    except AttributeError as e:
+        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
+
+
+def __dir__():
+    lazy_attrs = list(_dynamic_imports.keys())
+    return sorted(lazy_attrs)
+
 
 __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
-    "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingStreamOngoingSpeechResults",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/speech_to_text_translate_streaming/client.py

@@ -15,10 +15,6 @@ from .types.speech_to_text_translate_streaming_flush_signal import SpeechToTextT
 from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
-from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .types.speech_to_text_translate_streaming_stream_ongoing_speech_results import (
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-)
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -47,13 +43,10 @@ class SpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -69,9 +62,6 @@ class SpeechToTextTranslateStreamingClient:
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -84,12 +74,6 @@ class SpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
-
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -104,8 +88,6 @@ class SpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -114,12 +96,6 @@ class SpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
         ws_url = ws_url + f"?{query_params}"
         headers = self._raw_client._client_wrapper.get_headers()
         if api_subscription_key is not None:
@@ -164,13 +140,10 @@ class AsyncSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -186,9 +159,6 @@ class AsyncSpeechToTextTranslateStreamingClient:
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -201,12 +171,6 @@ class AsyncSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
-
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -221,8 +185,6 @@ class AsyncSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -231,12 +193,6 @@ class AsyncSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
         ws_url = ws_url + f"?{query_params}"
         headers = self._raw_client._client_wrapper.get_headers()
         if api_subscription_key is not None:

sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -14,10 +14,6 @@ from .types.speech_to_text_translate_streaming_flush_signal import SpeechToTextT
 from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
-from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .types.speech_to_text_translate_streaming_stream_ongoing_speech_results import (
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-)
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -35,13 +31,10 @@ class RawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -57,9 +50,6 @@ class RawSpeechToTextTranslateStreamingClient:
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -72,12 +62,6 @@ class RawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
-
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -92,8 +76,6 @@ class RawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -102,12 +84,6 @@ class RawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:
@@ -141,13 +117,10 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -163,9 +136,6 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
 
@@ -178,12 +148,6 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
-
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -198,8 +162,6 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -208,12 +170,6 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:

sarvamai/speech_to_text_translate_streaming/types/__init__.py

@@ -2,18 +2,45 @@
 
 # isort: skip_file
 
-from .speech_to_text_translate_streaming_flush_signal import SpeechToTextTranslateStreamingFlushSignal
-from .speech_to_text_translate_streaming_high_vad_sensitivity import SpeechToTextTranslateStreamingHighVadSensitivity
-from .speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .speech_to_text_translate_streaming_stream_ongoing_speech_results import (
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-)
-from .speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
+import typing
+from importlib import import_module
+
+if typing.TYPE_CHECKING:
+    from .speech_to_text_translate_streaming_flush_signal import SpeechToTextTranslateStreamingFlushSignal
+    from .speech_to_text_translate_streaming_high_vad_sensitivity import (
+        SpeechToTextTranslateStreamingHighVadSensitivity,
+    )
+    from .speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
+_dynamic_imports: typing.Dict[str, str] = {
+    "SpeechToTextTranslateStreamingFlushSignal": ".speech_to_text_translate_streaming_flush_signal",
+    "SpeechToTextTranslateStreamingHighVadSensitivity": ".speech_to_text_translate_streaming_high_vad_sensitivity",
+    "SpeechToTextTranslateStreamingVadSignals": ".speech_to_text_translate_streaming_vad_signals",
+}
+
+
+def __getattr__(attr_name: str) -> typing.Any:
+    module_name = _dynamic_imports.get(attr_name)
+    if module_name is None:
+        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
+    try:
+        module = import_module(module_name, __package__)
+        if module_name == f".{attr_name}":
+            return module
+        else:
+            return getattr(module, attr_name)
+    except ImportError as e:
+        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
+    except AttributeError as e:
+        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
+
+
+def __dir__():
+    lazy_attrs = list(_dynamic_imports.keys())
+    return sorted(lazy_attrs)
+
 
 __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
-    "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingStreamOngoingSpeechResults",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/text/client.py

@@ -47,7 +47,6 @@ class TextClient:
         speaker_gender: typing.Optional[TranslateSpeakerGender] = OMIT,
         mode: typing.Optional[TranslateMode] = OMIT,
         model: typing.Optional[TranslateModel] = OMIT,
-        enable_preprocessing: typing.Optional[bool] = OMIT,
         output_script: typing.Optional[TransliterateMode] = OMIT,
         numerals_format: typing.Optional[NumeralsFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -125,10 +124,6 @@ class TextClient:
             - mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
             - sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
 
-        enable_preprocessing : typing.Optional[bool]
-            This will enable custom preprocessing of the input text which can result in better translations.
-             Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
-
         output_script : typing.Optional[TransliterateMode]
             **output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
 
@@ -186,7 +181,6 @@ class TextClient:
             speaker_gender=speaker_gender,
             mode=mode,
             model=model,
-            enable_preprocessing=enable_preprocessing,
             output_script=output_script,
             numerals_format=numerals_format,
             request_options=request_options,
@@ -371,7 +365,6 @@ class AsyncTextClient:
         speaker_gender: typing.Optional[TranslateSpeakerGender] = OMIT,
         mode: typing.Optional[TranslateMode] = OMIT,
         model: typing.Optional[TranslateModel] = OMIT,
-        enable_preprocessing: typing.Optional[bool] = OMIT,
         output_script: typing.Optional[TransliterateMode] = OMIT,
         numerals_format: typing.Optional[NumeralsFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -449,10 +442,6 @@ class AsyncTextClient:
             - mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
             - sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
 
-        enable_preprocessing : typing.Optional[bool]
-            This will enable custom preprocessing of the input text which can result in better translations.
-             Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
-
         output_script : typing.Optional[TransliterateMode]
             **output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
 
@@ -518,7 +507,6 @@ class AsyncTextClient:
             speaker_gender=speaker_gender,
             mode=mode,
             model=model,
-            enable_preprocessing=enable_preprocessing,
             output_script=output_script,
             numerals_format=numerals_format,
             request_options=request_options,