diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
index 1d10fa1f9e..b83fe09305 100644
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@@ -573,9 +573,7 @@ def completion_cost( # noqa: PLR0915
base_model=base_model,
)
- verbose_logger.debug(
- f"completion_response _select_model_name_for_cost_calc: {model}"
- )
+ verbose_logger.info(f"selected model name for cost calculation: {model}")
if completion_response is not None and (
isinstance(completion_response, BaseModel)
diff --git a/litellm/llms/azure/audio_transcriptions.py b/litellm/llms/azure/audio_transcriptions.py
index 94793295ca..ba9ac01400 100644
--- a/litellm/llms/azure/audio_transcriptions.py
+++ b/litellm/llms/azure/audio_transcriptions.py
@@ -7,7 +7,11 @@ from pydantic import BaseModel
import litellm
from litellm.litellm_core_utils.audio_utils.utils import get_audio_file_name
from litellm.types.utils import FileTypes
-from litellm.utils import TranscriptionResponse, convert_to_model_response_object
+from litellm.utils import (
+ TranscriptionResponse,
+ convert_to_model_response_object,
+ extract_duration_from_srt_or_vtt,
+)
from .azure import (
AzureChatCompletion,
@@ -156,6 +160,8 @@ class AzureAudioTranscription(AzureChatCompletion):
stringified_response = response.model_dump()
else:
stringified_response = TranscriptionResponse(text=response).model_dump()
+ duration = extract_duration_from_srt_or_vtt(response)
+ stringified_response["duration"] = duration
## LOGGING
logging_obj.post_call(
diff --git a/litellm/proxy/_experimental/out/onboarding.html b/litellm/proxy/_experimental/out/onboarding.html
deleted file mode 100644
index ef020510ab..0000000000
--- a/litellm/proxy/_experimental/out/onboarding.html
+++ /dev/null
@@ -1 +0,0 @@
-LiteLLM Dashboard
\ No newline at end of file
diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml
index 83e71c55e1..a8de76184f 100644
--- a/litellm/proxy/_new_secret_config.yaml
+++ b/litellm/proxy/_new_secret_config.yaml
@@ -1,17 +1,9 @@
model_list:
- - model_name: gpt-3.5-turbo
+ - model_name: whisper
litellm_params:
- model: gpt-3.5-turbo
- - model_name: gpt-4o
- litellm_params:
- model: azure/gpt-4o
- api_key: os.environ/AZURE_API_KEY
- api_base: os.environ/AZURE_API_BASE
- - model_name: fake-openai-endpoint-5
- litellm_params:
- model: openai/my-fake-model
- api_key: my-fake-key
- api_base: https://exampleopenaiendpoint-production.up.railway.app/
- timeout: 1
-litellm_settings:
- fallbacks: [{"gpt-3.5-turbo": ["gpt-4o"]}]
+ model: azure/azure-whisper
+ api_version: 2024-02-15-preview
+ api_base: os.environ/AZURE_EUROPE_API_BASE
+ api_key: os.environ/AZURE_EUROPE_API_KEY
+ model_info:
+ mode: audio_transcription
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index a631ba963b..de1baad96f 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -947,7 +947,9 @@ def _set_spend_logs_payload(
spend_logs_url: Optional[str] = None,
):
verbose_proxy_logger.info(
- "Writing spend log to db - request_id: {}".format(payload.get("request_id"))
+ "Writing spend log to db - request_id: {}, spend: {}".format(
+ payload.get("request_id"), payload.get("spend")
+ )
)
if prisma_client is not None and spend_logs_url is not None:
if isinstance(payload["startTime"], datetime):