An
Apple Core AI export of NVIDIA's
parakeet-tdt-0.6b-v3,
for on-device speech recognition on Apple silicon.
A static encoder is the right default: a dynamic export re-specializes for every
new input length, and that cost is paid again on each process launch.
1import CirceKit
2
3let transcriber = CirceFileTranscriber(
4 backend: .coreAI(.bundle(bundleURL)),
5 locale: Locale(identifier: "en_US")
6)
7try await transcriber.prepare()
8let result = try await transcriber.transcribe(fileAt: audioURL)
9print(result.text)
1let model = try await SpeechRecognitionModel(resourcesAt: bundleURL)
2let (text, stats) = try await model.transcribe(audioURL: audioURL)
Released under
CC-BY-4.0, the
licence of the source model. The original Parakeet TDT 0.6B v3 is by
NVIDIA;
this repository only changes its serialization format. Refer to the
upstream model card for
training data, evaluation results, and intended use.
