Glimpse-Dictation/Whisper-Medium-coreml

Whisper Medium: Core ML encoder

This repository contains the optional Apple Silicon encoder for Whisper Medium in Glimpse. It is a companion to a Whisper GGUF or whisper.cpp ggml model, not a replacement for it: the model file still provides the decoder, tokenizer and metadata, and this package moves the audio encoder onto Core ML. Glimpse uses it for every Whisper Medium quantization.

File	Download size	Purpose
whisper-medium-encoder.mlmodelc.zip	568.6 MB	Compiled Core ML encoder

On Windows, Intel Macs, or anywhere without Core ML, use the model file on its own. The Core ML package requires Apple Silicon.

Provenance

The model originates from OpenAI Whisper Medium, licensed Apache 2.0. The encoder was converted from whisper.cpp's F16 ggml-medium.bin with scripts/convert-whisper-gguf-to-coreml.py from our transcribe.cpp fork, then zipped with ditto -c -k --keepParent.

Artifact	SHA-256
Encoder ZIP	59782b3aa871f498673266ae64990ee0d0a61adc59321656b9a266f5a3f7650b

Runtime requirements

Extract the ZIP next to the model file, keeping the whisper-medium-encoder.mlmodelc directory name. Glimpse-Speech looks for the companion beside the model and falls back to the model's own encoder when it isn't there.

The encoder follows Apple's Neural Engine transformer layout and computes in FP16. It takes one 30-second Whisper window. Core ML may run some operations on the CPU; this is not a guarantee of exclusive Neural Engine execution.

Glimpse

This encoder speeds up on-device dictation on Apple Silicon in Glimpse, a free, open-source dictation app for Mac and Windows. The source is on GitHub.