A desktop application for OpenAI's Whisper speech recognition model with a clean UI for transcribing audio files and realtime audio capture.
Create a models folder next to the executable and download Whisper model files (.bin format):
- Please download the models follow the instructions at ggml-org/whisper.cpp
Please first build ggml-org/whisper.cpp
Then set the environment variable WHISPER_ROOT to the cmake install dir or place the cmake install files at ../whisper