wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Pass input_audio_codec as an __init__ parameter

Browse Source
This commit is contained in:
shreyas-sarvam
2025-10-31 23:07:48 +05:30
parent 6c5d84ca4c
commit d905b21f72
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/pipecat/services/sarvam/stt.py
View File

@@ -78,14 +78,12 @@ class SarvamSTTService(STTService):
Only applicable to saaras (STT-Translate) models. Defaults to None. Only applicable to saaras (STT-Translate) models. Defaults to None.
vad_signals: Enable VAD signals in response. Defaults to True. vad_signals: Enable VAD signals in response. Defaults to True.
high_vad_sensitivity: Enable high VAD (Voice Activity Detection) sensitivity. Defaults to False. high_vad_sensitivity: Enable high VAD (Voice Activity Detection) sensitivity. Defaults to False.
input_audio_codec: Audio codec/format of the input file. Defaults to "wav".
""" """
language: Optional[Language] = None language: Optional[Language] = None
prompt: Optional[str] = None prompt: Optional[str] = None
vad_signals: bool = True vad_signals: bool = True
high_vad_sensitivity: bool = False high_vad_sensitivity: bool = False
input_audio_codec: str = "wav"
def __init__( def __init__(
self, self,
@@ -93,6 +91,7 @@ class SarvamSTTService(STTService):
api_key: str, api_key: str,
model: str = "saarika:v2.5", model: str = "saarika:v2.5",
sample_rate: Optional[int] = None, sample_rate: Optional[int] = None,
input_audio_codec: str = "wav",
params: Optional[InputParams] = None, params: Optional[InputParams] = None,
**kwargs, **kwargs,
): ):
@@ -102,6 +101,7 @@ class SarvamSTTService(STTService):
api_key: Sarvam API key for authentication. api_key: Sarvam API key for authentication.
model: Sarvam model to use for transcription. model: Sarvam model to use for transcription.
sample_rate: Audio sample rate. Defaults to 16000 if not specified. sample_rate: Audio sample rate. Defaults to 16000 if not specified.
input_audio_codec: Audio codec/format of the input file. Defaults to "wav".
params: Configuration parameters for Sarvam STT service. params: Configuration parameters for Sarvam STT service.
**kwargs: Additional arguments passed to the parent STTService. **kwargs: Additional arguments passed to the parent STTService.
""" """
@@ -140,7 +140,7 @@ class SarvamSTTService(STTService):
# Store connection parameters # Store connection parameters
self._vad_signals = params.vad_signals self._vad_signals = params.vad_signals
self._high_vad_sensitivity = params.high_vad_sensitivity self._high_vad_sensitivity = params.high_vad_sensitivity
self._input_audio_codec = params.input_audio_codec self._input_audio_codec = input_audio_codec
# Initialize Sarvam SDK client # Initialize Sarvam SDK client
self._sarvam_client = AsyncSarvamAI(api_subscription_key=api_key) self._sarvam_client = AsyncSarvamAI(api_subscription_key=api_key)