How to use language models
Selecting, downloading and packaging models
Currently, the plugin is designed to support a single language model, selected in the editor beforehand, to be packaged and used with the project. Follow these steps to select, download, and stage a specific language model:
- Choose the desired model size, which can be Tiny, Base, Small, Medium, or Large, including quantized versions which take up less space, and the language itself, which can be either Multilingual or English-only. Alternatively, specify the model size as Custom and provide a custom name for the language model and URL if you have your own language model to be downloaded from the server.
- Click on the Setup Language Model button, which will ask you to download the selected language model automatically if it is not already present on your local machine.
- After the download is complete, the Editor will generate a language model asset located at "Plugins/RuntimeSpeechRecognizer/Content/LanguageModels/LanguageModel.uasset". This language model asset will be the only one packaged with your project.
You can also remove any locally downloaded language models by clicking on the Clear Language Models button.
Alternatively, you can manually download and place language models only from https://huggingface.co/ggerganov/whisper.cpp into the "Plugins/RuntimeSpeechRecognizer/Content" folder.
Note that only the selected language model will be packaged with your project. Therefore, you don't need to worry about the other models as they will be excluded during the packaging phase.