WhisperSpeech
WhisperSpeech copied to clipboard
Update readme to show speed/tokens per second
Now that we have CUDA, basic MPS support, and CPU support...Is it possible to create a table or something on the github readme showing the speed. Initially it'll be scant, but eventually once it improves it'll be a source of comparison to others like Bark etc.
That's a good idea, I have a benchmark script we could adapt for that.
Ooh, can I have the script for my own testing? ;-)