phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add cost tracking + caching for transcription calls

Browse source
This commit is contained in:
Krrish Dholakia 2024-03-09 15:43:38 -08:00
parent e10991e02b
commit fa45c569fd
8 changed files with 225 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/llms/azure.py
View file

@ -861,7 +861,8 @@ class AzureChatCompletion(BaseLLM):
additional_args={"complete_input_dict": data},
original_response=stringified_response,
)
final_response = convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, response_type="audio_transcription") # type: ignore
hidden_params = {"model": "whisper-1", "custom_llm_provider": "azure"}
final_response = convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, hidden_params=hidden_params, response_type="audio_transcription") # type: ignore
return final_response
async def async_audio_transcriptions(
@ -921,7 +922,8 @@ class AzureChatCompletion(BaseLLM):
},
original_response=stringified_response,
)
response = convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, response_type="audio_transcription") # type: ignore
hidden_params = {"model": "whisper-1", "custom_llm_provider": "azure"}
response = convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, hidden_params=hidden_params, response_type="audio_transcription") # type: ignore
return response
except Exception as e:
## LOGGING