DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to speed up transcription on a Mac with the Neural Engine with Whisper CPP

Generate a Core ML encoder so Whisper CPP runs the encoder on the Apple Neural Engine, more than 3x faster than CPU only.

Short answer: Install the Python packages: pip install ane_transformers, pip install openai-whisper and pip install coremltools; then make sure Xcode is installed and run xcode-select --install for the command line tools; generate the encoder with ./models/generate-coreml-model.sh base.en, which creates models/ggml-base.en-encoder.mlmodelc. All steps.

  • Content
  • Intermediate
  • 45 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor

Who it is forA Mac user who transcribes often and wants the fastest local setup the hardware allows.

The problemCPU only transcription on a laptop is slow for long recordings and keeps the fans spinning.

The outcomewhisper-cli loading a Core ML encoder and transcribing noticeably faster on Apple Silicon.

What you need first

  • A C/C++ toolchain and CMake to build from source
  • ffmpeg to convert audio to 16-bit WAV, since whisper-cli reads 16-bit WAV files
  • Disk and RAM for the model you pick: about 142 MiB and 388 MB for base, up to 2.9 GiB and 3.9 GB for large
  • Optional: Xcode command line tools and Python 3.11 for Core ML on Apple Silicon

Steps

  1. Install the Python packages: pip install ane_transformers, pip install openai-whisper and pip install coremltools
  2. Make sure Xcode is installed and run xcode-select --install for the command line tools
  3. Generate the encoder with ./models/generate-coreml-model.sh base.en, which creates models/ggml-base.en-encoder.mlmodelc
  4. Build with Core ML: cmake -B build -DWHISPER_COREML=1 then cmake --build build -j --config Release
  5. Run ./build/bin/whisper-cli -m models/ggml-base.en.bin -f samples/jfk.wav and look for the Core ML model loaded line

Prompt for your agent

On my Apple Silicon Mac, set up ggml-org/whisper.cpp with Core ML support: install the Python requirements, generate the Core ML encoder for base.en, rebuild with WHISPER_COREML=1 and transcribe samples/jfk.wav. Tell me how long it took compared with the CPU build.

Caveat. The first run on a device is slow while the Neural Engine compiles the model, and the README recommends macOS Sonoma or newer to avoid transcription hallucination.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for ggml-org/whisper.cpp and "Speed up transcription on a Mac with the Neural Engine"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer