<< Click to display table of contents >> TRVFFmpegSpeechToTextProperty.ModelFileName

The file path of the whisper.cpp model (required).

property ModelFileName: TFileName;

You can download model files here: https://huggingface.co/ggerganov/whisper.cpp/tree/main

There are six model sizes, offering speed and accuracy tradeoff: tiny, base, small, medium, turbo, large.

Tiny, base, small, and medium models have English-only versions. The English models for English-only applications tend to perform better, especially for the tiny and base models. The difference becomes less significant for the small and medium models.

Whisper's performance varies widely depending on the language. More info: https://github.com/openai/whisper#available-models-and-languages

If the value of this property is changed during a speech recognition session, the new value is not used in that session. It will be used the next time speech recognition is run. See Active.

Default value:

'' (empty string)