[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:
co-authored by
gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Cyrus Leung
parent
6d09769700
commit
4eafc72928
@@ -23,9 +23,8 @@
|
||||
"""Inference-only Qwen3-ASR model."""
|
||||
|
||||
from collections.abc import Iterable, Mapping, Sequence
|
||||
from typing import Any, Literal
|
||||
from typing import Any
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from transformers.feature_extraction_utils import BatchFeature
|
||||
@@ -33,6 +32,7 @@ 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.inputs import ModalityData, MultiModalDataDict, PromptType, TokensPrompt
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.models.interfaces import (
|
||||
@@ -549,17 +549,12 @@ class Qwen3ASRForConditionalGeneration(
|
||||
)
|
||||
|
||||
@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_placeholder = cls.get_placeholder_str("audio", 0)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user