[SeoFood]

Thank you for testing TypeWhisper and the different models so thoroughly, and for sharing the results. Comparing several engines across multiple languages is already valuable; going one step further and building a faster Whisper Large v3 plugin is a real contribution.

This is exactly why I made TypeWhisper’s engine and plugin layer extensible. The best setup depends heavily on language, hardware, and workload. Your result that Large v3 can run close to Parakeet speeds on a modern Mac is especially interesting, as is your fully local Whisper plus Gemma correction workflow.

If you’re comfortable sharing the plugin or benchmark setup, I’d be very interested in taking a closer look and seeing whether it could benefit more users. Either way, thank you for putting so much time into this and contributing your findings back to the project.