FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities

Lilit Grigoryan, Vladimir Bataev, Nikolay Karpov, Andrei Andrusenko, Vitaly Lavrukhin +1 more
8/10/2025
eess.AScs.AIcs.CL

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognition

90% match1 repo912023

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding

79% match2025

Pushing the Limits of Beam Search Decoding for Transducer-based ASR models

76% match2025

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

76% match1 repo9.3k2023

Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition

75% match2025

Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting

75% match2024

Cite this paper

@article{grigoryan2025flexctc,
  title  = {FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities},
  author = {Lilit Grigoryan and Vladimir Bataev and Nikolay Karpov and Andrei Andrusenko and Vitaly Lavrukhin and Boris Ginsburg},
  year   = {2025},
  eprint = {2508.07315},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.07315v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.07315.svg)](https://codeofpaper.com/paper/2508.07315)

Discussion