ctc

Pruned CTC for Memory-Efficient Large-Vocabulary ASR Trainingarxiv.org

Pruned CTC limits CTC alignment calculations to the batch‑specific subset of tokens actually needed, eliminating the linear memory blow‑up with large vocabularies while preserving exact loss and gradient values. Applied to LLM‑based ASR, it cuts per‑step memory 5.1× with modest compute overhead and delivers near‑baseline WER at 7‑10× faster inference for both offline and bounded‑history streaming.