| ▲ | sipjca 5 hours ago | |
at first i got very excited about a new fast transcription model (voz) but turns out its just parakeet v3 with some new inference code which is macOS/iOS specific | ||
| ▲ | pveugen 4 hours ago | parent | next [-] | |
It's an ANE optimized version of Parakeet, with our own inference, which enabled us to push performance to about 300x realtime speed on an iPhone 16/17. Our next gen Voz model is trained from scratch and will be at least twice as fast. Android and other platforms will land soon. | ||
| ▲ | Muromec 3 hours ago | parent | prev | next [-] | |
Nice, now I know what I actually need. | ||
| ▲ | gorgmah 4 hours ago | parent | prev [-] | |
I was also thinking that this is almost too good to be true | ||