Verified record · from the answer index
nvidia/canary-qwen-2.5b
modeltested · static-verifiedscore 60/100signed passport ✓published 453d ago · verified 2026-10-2074,000 uses
🎤The best open-source speech-to-text model as of Jul 2025, transcribing audio with record 5.63% WER and enabling AI tasks like summarization directly from speech✨
Declared tools (1)
nvidia/canary-qwen-2.5b
model:replicate:nvidia/canary-qwen-2.5b