mlsanityData to 14 Oct 2026

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

arXiv 2508.07315 ↗First posted 10 Aug 2025eess.AS cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 10 Aug 2025.

Builds on

14 of 23 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2020Efficient Transformers: A Surveycited by 790
  4. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  5. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 150
  6. 2021SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognitioncited by 78
  7. 2018A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognitioncited by 66
  8. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 62
  9. 2022Flashlight: Enabling Innovation in Tools for Machine Learningcited by 25
  10. 2024MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decodercited by 7
  11. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  12. 2023GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognitioncited by 4
2 more
  1. 2025Pushing the Limits of Beam Search Decoding for Transducer-based ASR modelscited by 4
  2. 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Treecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wildcited by 2