Hugging Face Blog·· 18 h ago
Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
AI summary
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.
Selection record
Threshold 60Official, first-handFirst 38Second 42
Not admittedSum of both 80 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：开源语音识别与决策模型发布
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co