Faster Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
Portable version with WEB-UI for Windows machines.
Installation and launch
- Download all .zip.00X files.
- Unzip .zip.001 (preferably on SSD-drive)
- Run the file webui-start.bat.
- The interface will be opened in browser (localhost:7880)
PS:
- By default, only small model is pre-packed. If you select other models (large, medium), they will be loaded from the repository. The download process will be visible in the CLI window.
Unable to determine this model's library. Check the
docs
.