Hugging Face releases AnySpeechRecognizer and AnyDecisionModel for Apple platforms
AIHugging Face introduces two open Swift packages, AnySpeechRecognizer and AnyDecisionModel, for running speech recognition and yes-or-no, multiple-choice, and rating decisions on Apple devices. AnySpeechRecognizer keeps Apple's SpeechAnalyzer API and lets developers choose NVIDIA Parakeet or Alibaba Qwen3-ASR as the engine, with speaker diarization added.
AIWhy it matters.
The post shows how to swap speech engines and decision backends behind familiar Swift APIs, with measured accuracy and memory figures for each option.
Source details
Hugging Face Blog · huggingface.coPublished · added here
Original title: Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms