nvidia/canary-qwen-2.5b Automatic Speech Recognition β’ 3B β’ Updated 14 days ago β’ 25.3k β’ 335
Running on CPU Upgrade Featured 1.18k Open ASR Leaderboard π 1.18k View and request speech models benchmark data
Audio Source Separation Collection Also known as Music Source Separation (MSS), Stem Separation, Demixing, Audio Source Separation, or simply Unmixing. A branch of Signal Separation. β’ 2 items β’ Updated 8 days ago
Parakeet Collection NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants. β’ 12 items β’ Updated 6 days ago β’ 50
Jamba 1.5 Collection The AI21 Jamba family of models are state-of-the-art, hybrid SSM-Transformer instruction following foundation models β’ 2 items β’ Updated Mar 6 β’ 87
Runtime error Featured 185 Artist π¨ 185 Aesthetically Controllable Text-Driven Stylization w/o Train
Running Featured 121 Candle Segment Anything Wasm π― 121 Segment Anything Model on the Browser with Candle/Rust/WASM