<ul><li>NVIDIA AI has open-sourced two models: Canary 1B Flash and Canary 180M Flash for multilingual speech recognition and translation.</li><li>Both models utilize an encoder-decoder architecture with task-specific tokens and have scalable designs.</li><li>Canary 1B Flash achieves high performance with low word error rates and BLEU scores on various datasets.</li><li>The models support word-level and segment-level timestamping, enabling offline processing and on-device deployment.</li></ul>

NVIDIA AI Just Open Sourced Canary 1B and 180M Flash – Multilingual Speech Recognition and Translation Models

Discover more