Typhoon Isan ASR Whisper
Speech recognition model that delivers state-of-the-art accuracy for transcriptions of both Isan and general Thai speech
An open-source Thai speech recognition model specialized for the Isan dialect, Typhoon Isan ASR Whisper delivers accurate transcriptions of both Isan and general Thai speech. Fine-tuned from Biodatlab's Whisper Medium model, it addresses the critical gap in ASR systems that struggle with regional Thai dialects. Built on OpenAI's Whisper architecture, the model provides robust multilingual capabilities while adding specialized Isan dialect recognition. Optimized for accessibility and versatility, Typhoon Isan ASR Whisper democratizes quality speech-to-text for Thailand's Northeastern region—from educational institutions and local businesses to government services and enterprise deployments serving diverse linguistic communities.