nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 76.3k • 392
Extraction & Reconstruction for Efficient Speech Separation
Expressive Zeroshot TTS
Add a logo to anything
Chat with an AI assistant that thinks before answering
Generate creative Stable Diffusion prompts
Generate custom captions, tags, or prompts for any image
image2mesh
A Step Towards Music Generation Foundation Model
Interact with an AI agent to perform web tasks
Generate music powered by AI
3D-aware Video Diffusion for Video Generation Control
Generate images from text prompts