FluidAudio
An audio processing framework that may provide support for speech recognition models such as Parakeet, used for local audio inference.
Timeline (last 90 days)
The test bench calls WhisperKitEngine and ParakeetEngine in the application's core module, with dependencies pinned to WhisperKit 1.1.0 and FluidAudio 0.15.6.
The author notes that this benchmark covers only English, clean read speech, a single M4 machine, and is a snapshot (the application has since been upgraded to FluidAudio 0.15.8, which fixed an issue where the endings of some long recordings were discarded).
All Facts (2)
The test bench calls WhisperKitEngine and ParakeetEngine in the application's core module, with dependencies pinned to WhisperKit 1.1.0 and FluidAudio 0.15.6.
50%UnverifiedThe author notes that this benchmark covers only English, clean read speech, a single M4 machine, and is a snapshot (the application has since been upgraded to FluidAudio 0.15.8, which fixed an issue where the endings of some long recordings were discarded).
50%