AnySpeechRecognizer and AnyDecisionModel packages enable local speech transcription and structured decision-making on Apple platforms
New packages for Apple platforms allow developers to choose a speech transcription model, distinguish between speakers, and obtain typed responses with probabilities. Open models can be downloaded from Hugging Face Hub and run directly on the device.
Deploying local transcription in business applications requires planning for model downloads and storage capacity on devices. The choice of model also determines the licensing terms.