Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms

Two new open-source Swift packages, AnySpeechRecognizer and AnyDecisionModel, have been introduced for Apple platforms. AnySpeechRecognizer provides a speech-to-text API compatible with Apple's framework but allows using open models like NVIDIA's Parakeet and Alibaba's Qwen3-ASR, which run locally via Core ML and add speaker diarization. AnyDecisionModel is designed for classification tasks, answering yes-or-no or multiple-choice questions with typed results and probabilities using on-device models. Both packages can download open models from the Hugging Face Hub to run directly on Apple devices.