Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
- ID
- 40710
- Status
- summarized
- Published
- 29 Oct 2026, 8:00 AM
- Fetched
- 29 Oct 2026, 9:15 PM
- Provider
- Hugging Face Blog
- Category
- developer-ai
- Original URL
- https://huggingface.co/blog/anydecisionmodel
- Source URL
- https://huggingface.co/blog/feed.xml
Summary
- Score
- 6.0
- Created
- 29 Oct 2026, 9:15 PM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Hugging Face published two Swift packages, AnySpeechRecognizer and AnyDecisionModel, that mirror Apple's new SpeechAnalyzer API (introduced in macOS 26 / iOS 26) but let you swap the recognition engine — Apple's Speech framework by default, or NVIDIA Parakeet v3 and Alibaba Qwen3-ASR running locally on Core ML — while adding speaker diarization via SpeechDetector. AnyDecisionModel answers yes/no, multiple-choice and rating-scale questions with typed results and probabilities, derived from model probabilities rather than generated text, running on-device through MLX, Core AI or llama.cpp, or against Jev or Ollama. Both packages pull open models from the Hugging Face Hub; the post is by 'mattt' and is a package announcement, with no accuracy benchmarks or latency numbers included.
Why it matters
If you ship iOS/macOS 26 apps, the claim is that changing the import from Speech to AnySpeechRecognizer keeps your SpeechTranscriber / AssetInventory code intact, so you can move audio off a cloud ASR bill and onto Parakeet or Qwen3-ASR on device — and get diarization you don't get from Apple's engine alone. For classification tasks (routing, triage, ratings), AnyDecisionModel gives you typed answers plus probabilities instead of parsing generated text, which is a concrete design choice to weigh against prompting an LLM. Caveat: no benchmarks or version pins are given here, so treat the 'one import change' claim as untested until you run your own audio through both engines.
Discussion angle
For a support-call triage flow, where is the line between a small probability-returning decision model and just prompting an LLM — and does the 'swap the import, keep the code' promise for ASR engines hold up once you test Parakeet v3 against Apple's SpeechTranscriber on your own audio?