Speech Recognition Channel Integration with faster-whisper-xxl.exe

The speech recognition channel now integrates Purfview/whisper-standalone-win, which is faster-whisper-xxl.exe.

You can download the tool from the following address: https://github.com/Purfview/whisper-standalone-win/releases

After downloading and extracting the file, select faster-whisper-xxl.exe in the speech recognition channel. In the pop-up selection box, find the location of faster-whisper-xxl.exe to start using it.

Tip: faster-whisper-xxl.exe supports a large number of parameters. To maintain flexibility, the software only includes the required parameters: model, language, and output format. You can create a file named pyvideotrans.txt in the same directory as faster-whisper-xxl.exe and add other parameters to the file. The file format should follow the requirements of xxl.exe. Note that you should not add the model size, language, and output format parameters again, as this will cause errors.

For example: