Deepgram Transcriber Language Support Issue

[Riya-766]

I encountered an issue with the Deepgram transcriber when configuring it to use a Spanish language. Below is a snippet of the code used and the resulting error:

**from vocode.streaming.models.transcriber import DeepgramTranscriberConfig

transcriber_config = DeepgramTranscriberConfig.from_telephone_input_device( language="es", model="nova-2" ) transcriber_factory = DefaultTranscriberFactory()**

Error:

vocode.streaming.utils.create_task:log_if_exception:12 - Vocode wrapped logger; exception raised by task <Task finished name='Task-16' coro=<DeepgramTranscriber._run_loop() done, defined at C:\Users\path\to\file\deepgram_transcriber.py:171> exception=AssertionError()>: NoneType: None

Issue:

It appears that the Deepgram transcriber is not functioning with languages other than English. This issue prevents the use of the transcriber for other languages as intended.

[shalini2111]

I'm also experiencing the same issue when trying to configure the Deepgram transcriber for the Spanish language. The AssertionError appears when I set the language parameter to "es" with the model set to "nova-2". Has anyone found a workaround or solution for this? Any guidance would be appreciated.

[Hruthkarsha]

While setting up the Deepgram transcriber for French, I'm running across a similar problem. I get error an when I use the model "nova" and change the language option to "fr". Has someone found a fix or a workaround for this issue? Any advice or insights would be very valued.I have also modified language and model in transcriber,py class DeepgramTranscriberConfig(TranscriberConfig, type=TranscriberType.DEEPGRAM.value): # type: ignore language: Optional[str] = "fr" model: Optional[str] = "nova" tier: Optional[str] = None version: Optional[str] = None keywords: Optional[list] = None api_key: Optional[str] = None on_prem: bool = False ws_url: str = DEEPGRAM_API_WS_URL

Exception raised by task <Task finished name='Task-16' coro=<DeepgramTranscriber._run_loop() done, defined at C:\Users\\vocode-core-updated\vocode-core-3\vm\vocode\streaming\transcriber\deepgram_transcriber.py:171> exception=InvalidStatusCode(400, Headers([('content-type', 'application/json'), ('dg-error', "Invalid 'tier' value of 'nova'."), ('content-length', '136'), ('access-control-allow-credentials', 'true'), ('vary', 'origin'), ('vary', 'access-control-request-method'), ('vary', 'access-control-request-headers'), ('access-control-expose-headers', 'dg-model-name,dg-model-uuid,dg-char-count,dg-request-id,dg-error'), ('dg-request-id')>: server rejected WebSocket connection: HTTP 400 NoneType: None

[Riya-766]

@arpagon, @ajar98 can you please help?

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.