FermionResearch/Phonon-2-CoreML开源了新模型

Fermion Research FermionResearch/Phonon-2-CoreML FermionResearch/Phonon-2-CoreML https://huggingface.co/FermionResearch/Phonon-2-CoreML

FermionResearch/Phonon-2-CoreML · Hugging Face Hugging Face (https://huggingface.co/) Models (https://huggingface.co/models) Datasets (https://huggingface.co/datasets) Spaces (https://huggingface.co/spaces) Buckets new (https://huggingface.co/storage) Docs (https://huggingface.co/docs) Enterprise (https://huggingface.co/enterprise) Pricing (https://huggingface.co/pricing) Website Tasks (https://huggingface.co/tasks) HuggingChat (https://huggingface.co/chat) Collections (https://huggingface.co/collections) Languages (https://huggingface.co/languages) Organizations (https://huggingface.co/organizations) Community Blog (https://huggingface.co/blog) Posts (https://huggingface.co/posts) Daily Papers (https://huggingface.co/papers) Hardware (https://huggingface.co/hardware) Learn (https://huggingface.co/learn) Discord (https://huggingface.co/join/discord) Forum (https://discuss.huggingface.co/) GitHub (https://github.com/huggingface) Solutions Team & Enterprise (https://huggingface.co/enterprise) Hugging Face PRO (https://huggingface.co/pro) Enterprise Support (https://huggingface.co/support) Inference Providers (https://huggingface.co/inference/models) Inference Endpoints (https://huggingface.co/inference-endpoints) Storage Buckets (https://huggingface.co/storage) Log In (https://huggingface.co/login) Sign Up (https://huggingface.co/join) (https://huggingface.co/FermionResearch) FermionResearch (https://huggingface.co/FermionResearch) / Phonon-2-CoreML (https://huggingface.co/FermionResearch/Phonon-2-CoreML) Like 1 Automatic Speech Recognition (https://huggingface.co/models?pipeline_tag=automatic-speech-recognition) Core ML (https://huggingface.co/models?library=coreml) English (https://huggingface.co/models?language=en) neural-engine (https://huggingface.co/models?other=neural-engine) apple-silicon (https://huggingface.co/models?other=apple-silicon) speech-to-text (https://huggingface.co/models?other=speech-to-text) asr (https://huggingface.co/models?other=asr) stt (https://huggingface.co/models?other=stt) on-device (https://huggingface.co/models?other=on-device) License: cc-by-4.0 Model card (https://huggingface.co/FermionResearch/Phonon-2-CoreML) Files Files and versions xet (https://huggingface.co/FermionResearch/Phonon-2-CoreML/tree/main) Community (https://huggingface.co/FermionResearch/Phonon-2-CoreML/discussions) Copy to bucket new Phonon-2 Core ML (https://huggingface.co/FermionResearch/Phonon-2-CoreML#phonon-2-core-ml) Run it (https://huggingface.co/FermionResearch/Phonon-2-CoreML#run-it) Long audio (https://huggingface.co/FermionResearch/Phonon-2-CoreML#long-audio) Accuracy (https://huggingface.co/FermionResearch/Phonon-2-CoreML#accuracy) Speed (https://huggingface.co/FermionResearch/Phonon-2-CoreML#speed) Files (https://huggingface.co/FermionResearch/Phonon-2-CoreML#files) Licence (https://huggingface.co/FermionResearch/Phonon-2-CoreML#licence) (https://huggingface.co/FermionResearch/Phonon-2-CoreML#phonon-2-core-ml) Phonon-2 Core ML Phonon-2 for the Apple Neural Engine. The Core ML package reads with the accuracy of the Phonon-2 reference engine: on the Open ASR Leaderboard's seven English test sets, run with the leaderboard's own code on the full sets, it averages 5.21 % word error, with LibriSpeech test-clean at 1.73 % and test-other at 3.91 %. On an M5 MacBook Air an hour of speech becomes text in 6 seconds (606 times realtime), a few seconds of audio returns its text in about 11 milliseconds once the model is loaded, every word carries its start and end time, and the GPU stays free. (https://huggingface.co/FermionResearch/Phonon-2-CoreML#run-it) Run it Phonon-2 is the model inside Detta (https://www.fermionresearch.com/products/detta) , the dictation app for the Mac. This repository runs it on the Neural Engine from Swift or Python. Download the model folder with the Hugging Face command line, in a virtual environment with Python 3.10 to 3.13 (macOS's built-