Problem
Research questions and friction points this paper is trying to address.
speech transcription
historical context
intra-audio batching
Word Error Rate (WER)
Context-Aware Interleaved Batching for WhisperX
🤖 AI Summary
为解决WhisperX丢失历史上下文和标准Whisper推理慢的问题，提出基于VAD的上下文感知交错批处理方法，降低词错误率并提高专有名词转录准确性。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Context-Aware Interleaved Batching
VAD-derived segment boundaries
historical context
Word Error Rate (WER)
high-throughput inference
🔎 Similar Papers
No similar papers found.
