phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +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 f2df53771c
commit d58fe5a9f9
20 changed files with 402 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

26
litellm/llms/openai/transcriptions/handler.py
View file

@ -7,6 +7,9 @@ from pydantic import BaseModel
import litellm
from litellm.litellm_core_utils.audio_utils.utils import get_audio_file_name
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.llms.base_llm.audio_transcription.transformation import (
BaseAudioTranscriptionConfig,
)
from litellm.types.utils import FileTypes
from litellm.utils import (
TranscriptionResponse,
@ -75,6 +78,7 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
model: str,
audio_file: FileTypes,
optional_params: dict,
litellm_params: dict,
model_response: TranscriptionResponse,
timeout: float,
max_retries: int,
@ -83,16 +87,24 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
api_base: Optional[str],
client=None,
atranscription: bool = False,
provider_config: Optional[BaseAudioTranscriptionConfig] = None,
) -> TranscriptionResponse:
data = {"model": model, "file": audio_file, **optional_params}
if "response_format" not in data or (
data["response_format"] == "text" or data["response_format"] == "json"
):
data["response_format"] = (
"verbose_json" # ensures 'duration' is received - used for cost calculation
"""
Handle audio transcription request
"""
if provider_config is not None:
data = provider_config.transform_audio_transcription_request(
model=model,
audio_file=audio_file,
optional_params=optional_params,
litellm_params=litellm_params,
)
if isinstance(data, bytes):
raise ValueError("OpenAI transformation route requires a dict")
else:
data = {"model": model, "file": audio_file, **optional_params}
if atranscription is True:
return self.async_audio_transcriptions( # type: ignore
audio_file=audio_file,