How to Use Whisper_CPP

whisper.cpp is a C++ implementation version of the Whisper model.

Download the whisper.cpp Main Program

First, you need to download the corresponding precompiled version based on your operating system and hardware.

Download Address: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.2

How to choose?

• Windows (without NVIDIA GPU): Download whisper-bin-x64.zip.
• Windows (with NVIDIA GPU): Please choose based on your installed CUDA version. For example, if you have CUDA 12.x installed, download whisper-cublas-12.4.0-bin-x64.zip; if you have CUDA 11.x installed, download whisper-cublas-11.8.0-bin-x64.zip. Using GPU acceleration can greatly improve transcription speed.
• macOS Users: Download whisper-v1.8.2-xcframework.zip.

Extract and Organize the File Structure

After downloading, extract the compressed file. It is strongly recommended to extract it to a short path that does not contain Chinese characters or spaces, for example, D:\whispercpp. This can avoid many unnecessary issues.

After extraction, enter the folder and make sure you can see a file named whisper-cli.exe.

Using in pyvideotrans

Click on the pyvideotrans menu -> Voice Recognition Settings -> Whisper_CPP -> Click "Select whisper-cli", find your extracted whisper-cli.exe file, and then save.