# Hugging Face — Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms

- Company: Hugging Face (huggingface.co)
- Announced: 2026-10-29
- Category: developer-tool-release
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/anydecisionmodel
- Record: https://forck.live/items/29280-introducing-anyspeechrecognizer-and-anydecisionmodel-open-models-for-speech
- Subject: Platform
- Models affected: Parakeet v3, Parakeet Ultra, Parakeet Unified, Qwen3-ASR, Sortformer

Two Swift packages, AnySpeechRecognizer and AnyDecisionModel, extend the approach of AnyLanguageModel and swift-huggingface to speech and decisions on Apple platforms. AnySpeechRecognizer keeps Apple's new SpeechAnalyzer API but lets developers choose the recognition engine, including NVIDIA's Parakeet and Alibaba's Qwen3-ASR running locally on Core ML. It also adds speaker diarization, which Apple's Speech framework lacks, using NVIDIA's Streaming Sortformer to track up to four speakers even when they talk over each other. AnyDecisionModel answers yes-or-no, multiple-choice and rating-scale questions with typed results and probabilities, deriving each answer from the model's probabilities instead of generating text. Both packages can download open models from the Hugging Face Hub and run them on device, with downloads happening only when the app asks. Parakeet v3 recognizes 25 European languages and detects which one it hears, while Qwen3-ASR covers 30 languages and 22 Chinese dialects but runs on the GPU and is slower, suiting file transcription over live input.

## Evidence

Verbatim from https://huggingface.co/blog/anydecisionmodel:

> Language models can do a lot. They write, summarize, translate, and call tools. But they're only a small part of what machine learning can do.
> 
> Say a customer calls your support line. First, you want to know what they said (speech recognition). Then, you want to decide where to send them (decision). You could hand both to a language model, but there are models built for each that are better, faster, and less expensive.
> 
> In our AnyLanguageModel 1.0 recap , we looked at a year of local and hosted models in Swift. With AnyLanguageModel and swift-huggingface now on their 1.x releases, we're extending the same approach to speech and decisions: familiar Swift APIs with a choice of model.
> 
> Today we're announcing two packages:
> 
> AnySpeechRecognizer implements Apple's new speech-to-text API with a choice of recognition engine, including NVIDIA's Parakeet and Alibaba's Qwen3-ASR running locally on Core ML, and adds speaker diarization to track who speaks when.
> 
> AnyDecisionModel answers yes-or-no, multiple-choice, and rating-scale questions with typed results and probabilities.

---

Record: https://forck.live/items/29280-introducing-anyspeechrecognizer-and-anydecisionmodel-open-models-for-speech
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md