SOURCE-LINKED INTELLIGENCE

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as live captioning and voice agents. We present a deployable system for streaming Thai ASR that lets a user steer its vocabulary at decode time, without retraining. A widely used open Thai model, trained with full context, collapses when run as a true stream; we restore streaming with a cache-aware encoder, by converting it or adapting a natively streaming one, and add a shallow-fusion layer that re-ranks candidates insid

Read original source ↗ Open in workspace

recordType

paper

region

Global