VibeVoiceASRProcessor (vibevoice_asr_processor.py)

Processor class for VibeVoice ASR models.

"""
Processor class for VibeVoice ASR models.
"""

import os
import json
import math
import warnings
from typing import List, Optional, Union, Dict, Any, Tuple

import numpy as np
import torch

from transformers.tokenization_utils_base import BatchEncoding
from transformers.utils import TensorType, logging
from .vibevoice_tokenizer_processor import VibeVoiceTokenizerProcessor, AudioNormalizer

try:
    from .audio_utils import load_audio_use_ffmpeg
    HAS_FFMPEG_UTILS = True
except ImportError:
    HAS_FFMPEG_UTILS = False
    warnings.warn("audio_utils not available, will fall back to soundfile for audio loading")

logger = logging.get_logger(__name__)

SYSTEM_PROMPT = "You are a helpful assistant that transcribes audio input into text output in JSON format."


def _ships_tokenizer(pretr

... (truncated -- full source via MCP)