As an upgrade option from the Small model, we have bundled ggml-large-v3-turbo-q5_0.bin.
Large Turbo is a faster model that maintains accuracy while supporting multiple languages, and q5_0 is lightweight, making load time and inference performance more practical.
To use it, simply select ggml-large-v3-turbo-q5_0.bin from the tray menu under Models after launching the app.
You can also download and try other models from the link above.
https://huggingface.co/ggerganov/whisper.cpp/tree/main
