Parakeet is incredibly fast and accurate even on CPU, and it supports streaming now also in TDT3.
Apple likely needed a model that ran on their NPU natively.
- parakeet usually runs on Bfloat16. NPU doesn't support that
- CPU is not as fast as the NPU for these ops on A-series, and even on modern CPUs, there's a latency delay
- Parakeet latency is fine but "fine" may not be good enough for Apple's UX team.
- CPU increases power consumption over dedicated float blocks
So I would say that Parakeet was a non-option for Apple to ship, although it should be in the benchmarks anyways!
alt Hacker News
Apple likely needed a model that ran on their NPU natively.
- parakeet usually runs on Bfloat16. NPU doesn't support that
- CPU is not as fast as the NPU for these ops on A-series, and even on modern CPUs, there's a latency delay
- Parakeet latency is fine but "fine" may not be good enough for Apple's UX team.
- CPU increases power consumption over dedicated float blocks
So I would say that Parakeet was a non-option for Apple to ship, although it should be in the benchmarks anyways!