phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add OpenAI gpt-4o-transcribe support (#9517)

Browse source 
* refactor: introduce new transformation config for gpt-4o-transcribe models

* refactor: expose new transformation configs for audio transcription

* ci: fix config yml

* feat(openai/transcriptions): support provider config transformation on openai audio transcriptions

allows gpt-4o and whisper audio transformation to work as expected

* refactor: migrate fireworks ai + deepgram to new transform request pattern

* feat(openai/): working support for gpt-4o-audio-transcribe

* build(model_prices_and_context_window.json): add gpt-4o-transcribe to model cost map

* build(model_prices_and_context_window.json): specify what endpoints are supported for `/audio/transcriptions`

* fix(get_supported_openai_params.py): fix return

* refactor(deepgram/): migrate unit test to deepgram handler

* refactor: cleanup unused imports

* fix(get_supported_openai_params.py): fix linting error

* test: update test
This commit is contained in:
Krish Dholakia 2025-03-26 23:10:25 -07:00 • committed by GitHub
parent 109add7946
commit c0845fec1f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 402 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/main.py
View file

@ -5095,6 +5095,12 @@ def transcription(
response: Optional[
Union[TranscriptionResponse, Coroutine[Any, Any, TranscriptionResponse]]
] = None
provider_config = ProviderConfigManager.get_provider_audio_transcription_config(
model=model,
provider=LlmProviders(custom_llm_provider),
)
if custom_llm_provider == "azure":
# azure configs
api_base = api_base or litellm.api_base or get_secret_str("AZURE_API_BASE")
@ -5161,12 +5167,15 @@ def transcription(
max_retries=max_retries,
api_base=api_base,
api_key=api_key,
provider_config=provider_config,
litellm_params=litellm_params_dict,
)
elif custom_llm_provider == "deepgram":
response = base_llm_http_handler.audio_transcriptions(
model=model,
audio_file=file,
optional_params=optional_params,
litellm_params=litellm_params_dict,
model_response=model_response,
atranscription=atranscription,
client=(
@ -5185,6 +5194,7 @@ def transcription(
api_key=api_key,
custom_llm_provider="deepgram",
headers={},
provider_config=provider_config,
)
if response is None:
raise ValueError("Unmapped provider passed in. Unable to get the response.")