Could you clarify what you'd like to do with ggmlmediumbin ? I'm happy to provide the exact commands or fix the filename if needed.
On an (8 threads, no GPU):
It features 24 audio layers and 24 text layers , providing a significant jump in complexity from the "Small" or "Base" models. Performance vs. Accuracy: The Medium Trade-off ggmlmediumbin work
: If you haven't already, you can use the built-in script in the Whisper.cpp repository : ./models/download-ggml-model.sh medium Use code with caution. Copied to clipboard Could you clarify what you'd like to do with ggmlmediumbin