[论文] Context-Aware Interleaved Batching for WhisperX

论文概要

研究领域: NLP 作者: Carlos Bain, Max Bain 发布时间: 2025-09-01 arXiv: 2509.00138

中文摘要

WhisperX通过音频内批处理加速语音转录，但会将音频段隔离，丢失了连贯标点和术语转录所需的历史上下文。相反，标准Whisper按顺序保留上下文，但推理速度慢且容易产生幻觉循环。为兼顾两者优势，我们提出上下文感知交错批处理。通过使用VAD派生的段边界，我们的算法稳定了Whisper的文本条件，使我们能够在批处理音频段之间安全地保持连续的历史上下文。在长音频基准测试上的实验表明，该方法降低了词错误率（WER）并改进了专有名词转录，同时保持了高吞吐量的推理速度。

原文摘要

While WhisperX accelerates speech transcription via intra-audio batching, it isolates audio segments, losing the historical context needed for coherent punctuation and terminology transcription. Conversely, standard Whisper retains context sequentially but suffers from slow inference and hallucination loops. To achieve the best of both worlds, we propose Context-Aware Interleaved Batching. By using VAD-derived segment boundaries, our algorithm stabilizes Whisper's text conditioning, allowing us to safely maintain continuous historical context across batched audio segments. As demonstrated on long-form audio benchmarks, this approach reduces Word Error Rate (WER) and improves proper noun transcription, all while maintaining high-throughput inference speeds.

#论文 #arXiv #NLP #小凯