[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
+6 -11
View File
@@ -4,7 +4,6 @@
from collections.abc import Iterable, Mapping, Sequence
from typing import Annotated, Any, Literal, TypeAlias
import numpy as np
import torch
import torch.nn as nn
from transformers import BatchFeature
@@ -13,6 +12,7 @@ from transformers.models.whisper import WhisperFeatureExtractor
from vllm.config import ModelConfig, SpeechToTextConfig, VllmConfig
from vllm.config.multimodal import BaseDummyOptions
from vllm.config.speech_to_text import SpeechToTextParams
from vllm.distributed.parallel_state import get_tensor_model_parallel_world_size
from vllm.inputs import ModalityData, MultiModalDataDict, PromptType, TokensPrompt
from vllm.model_executor.layers.activation import get_act_fn
@@ -1131,17 +1131,12 @@ class GlmAsrForConditionalGeneration(
)
@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:
"""Get the generation prompt to be used for transcription requests."""
audio = stt_params.audio
model_config = stt_params.model_config
task_type = stt_params.task_type
to_language = stt_params.to_language
tokenizer = cached_tokenizer_from_config(model_config)
audio_token = cls._get_audio_token(model_config)