Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition
This work addresses a critical gap in real-time Thai ASR for applications requiring low latency, though it is incremental in adapting existing methods to a specific language and domain.
The authors tackled the lack of efficient streaming solutions for Thai automatic speech recognition by developing a compact FastConformer-Transducer model, achieving a 45x reduction in computational cost compared to Whisper Large-v3 while maintaining comparable accuracy through rigorous text normalization.
Large encoder-decoder models like Whisper achieve strong offline transcription but remain impractical for streaming applications due to high latency. However, due to the accessibility of pre-trained checkpoints, the open Thai ASR landscape remains dominated by these offline architectures, leaving a critical gap in efficient streaming solutions. We present Typhoon ASR Real-time, a 115M-parameter FastConformer-Transducer model for low-latency Thai speech recognition. We demonstrate that rigorous text normalization can match the impact of model scaling: our compact model achieves a 45x reduction in computational cost compared to Whisper Large-v3 while delivering comparable accuracy. Our normalization pipeline resolves systemic ambiguities in Thai transcription --including context-dependent number verbalization and repetition markers (mai yamok) --creating consistent training targets. We further introduce a two-stage curriculum learning approach for Isan (north-eastern) dialect adaptation that preserves Central Thai performance. To address reproducibility challenges in Thai ASR, we release the Typhoon ASR Benchmark, a gold-standard human-labeled datasets with transcriptions following established Thai linguistic conventions, providing standardized evaluation protocols for the research community.