[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
+8 -9
View File
@@ -26,9 +26,8 @@
import math
from collections.abc import Iterable, Mapping
from typing import Annotated, Literal
from typing import Annotated
import numpy as np
import torch
import torch.nn.functional as F
from torch import nn
@@ -36,6 +35,7 @@ from transformers import BatchFeature, PretrainedConfig
from vllm.config import CacheConfig, ModelConfig, SpeechToTextConfig, VllmConfig
from vllm.config.multimodal import BaseDummyOptions
from vllm.config.speech_to_text import SpeechToTextParams
from vllm.inputs import MultiModalDataDict, PromptType, TokensPrompt
from vllm.model_executor.layers.linear import ColumnParallelLinear, RowParallelLinear
from vllm.model_executor.layers.quantization import QuantizationConfig
@@ -852,15 +852,14 @@ class GraniteSpeechForConditionalGeneration(
@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,
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
# Audio placeholders don't use an index, so value doesn't matter
audio_tok = cls.get_placeholder_str("audio", 0)