[Audio] Bundle get_generation_prompt() params into SpeechToTextParams (#36268)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Ekagra Ranjan
2026-04-22 12:24:18 +08:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Cyrus Leung
parent 6d09769700
commit 4eafc72928
18 changed files with 214 additions and 161 deletions
+7 -10
View File
@@ -14,6 +14,7 @@ from transformers import WhisperConfig as HFWhisperConfig
from vllm.config import ModelConfig, SpeechToTextConfig, VllmConfig
from vllm.config.multimodal import BaseDummyOptions
from vllm.config.speech_to_text import SpeechToTextParams
from vllm.inputs import PromptType, TokensPrompt
from vllm.model_executor.model_loader import DefaultModelLoader
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
@@ -626,16 +627,12 @@ class KimiAudioForConditionalGeneration(
)
@classmethod
def get_generation_prompt(
cls,
audio: np.ndarray,
model_config: ModelConfig,
stt_config: SpeechToTextConfig,
language: str | None,
task_type: Literal["transcribe", "translate"],
request_prompt: str,
to_language: str | None,
) -> PromptType:
def get_generation_prompt(cls, stt_params: SpeechToTextParams) -> PromptType:
audio = stt_params.audio
model_config = stt_params.model_config
task_type = stt_params.task_type
request_prompt = stt_params.request_prompt
tokenizer = cached_get_tokenizer(
model_config.tokenizer,
tokenizer_cls=KimiAudioTokenizer,