用GPU加速语音识别解码，速度更快且支持上下文增强。
FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities
- 全GPU实现，避免CPU-GPU同步瓶颈，提升解码效率。
- 支持N-gram语言模型融合与短语级增强，提升识别准确率。
- 开源易用，适合研究和生产环境快速部署。
虽然束搜索比贪婪解码能提升语音识别质量，但传统实现通常缓慢、串行且依赖CPU。为充分发挥现代硬件性能，我们提出开源的FlexCTC工具包，实现连接时序分类（CTC）模型的全GPU束搜索解码。该工具包基于Python和PyTorch构建，提供高速、易用且可扩展的替代方案，无需使用C++、CUDA或WFST。其核心为高性能全批处理GPU实现，通过CUDA Graph减少内核启动开销，并消除CPU-GPU同步延迟。同时支持高级上下文技术，包括GPU加速的N-gram语言模型融合与短语级增强。这些特性使解码既准确又高效，适用于研究与生产场景。
原文摘要 · Abstract (English)
While beam search improves speech recognition quality over greedy decoding, standard implementations are slow, often sequential, and CPU-bound. To fully leverage modern hardware capabilities, we present a novel open-source FlexCTC toolkit for fully GPU-based beam decoding, designed for Connectionist Temporal Classification (CTC) models. Developed entirely in Python and PyTorch, it offers a fast, user-friendly, and extensible alternative to traditional C++, CUDA, or WFST-based decoders. The toolkit features a high-performance, fully batched GPU implementation with eliminated CPU-GPU synchronization and minimized kernel launch overhead via CUDA Graphs. It also supports advanced contextualization techniques, including GPU-powered N-gram language model fusion and phrase-level boosting. These features enable accurate and efficient decoding, making them suitable for both research and production use.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。