[Frontend] Consolidate Speech to Text entrypoints. (#42370)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-05-12 07:06:57 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 8517cdaf90
commit d37e25ffbe
26 changed files with 681 additions and 607 deletions
@@ -0,0 +1,60 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from http import HTTPStatus
from typing import Annotated
from fastapi import APIRouter, Form, Request
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.utils import (
load_aware_call,
with_cancellation,
)
from vllm.logger import init_logger
from .protocol import TranslationRequest, TranslationResponseVariant
from .serving import OpenAIServingTranslation
logger = init_logger(__name__)
router = APIRouter()
def translation(request: Request) -> OpenAIServingTranslation:
return request.app.state.openai_serving_translation
@router.post(
"/v1/audio/translations",
responses={
HTTPStatus.OK.value: {"content": {"text/event-stream": {}}},
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
HTTPStatus.UNPROCESSABLE_ENTITY.value: {"model": ErrorResponse},
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
},
)
@with_cancellation
@load_aware_call
async def create_translations(
request: Annotated[TranslationRequest, Form()], raw_request: Request
):
handler = translation(raw_request)
if handler is None:
raise NotImplementedError("The model does not support Translations API")
audio_data = await request.file.read()
generator = await handler.create_translation(audio_data, request, raw_request)
if isinstance(generator, ErrorResponse):
return JSONResponse(
content=generator.model_dump(), status_code=generator.error.code
)
elif isinstance(generator, TranslationResponseVariant):
return JSONResponse(content=generator.model_dump())
return StreamingResponse(content=generator, media_type="text/event-stream")