- it is very fast and scales quite nicely on CPU with 4 threads (~ twice the speed), but not further (I tried it on a 64 cores box). Not sure why since they seem to be using torch's native threading support.
- surprisingly, it is not that much faster when run on a GPU
- the quality (as in: what I'm hearing, not a formally measured metric) is good but (YMMV) not as good as turtle.
- it breaks with strange error messages if the text you feed it is too long
- there is mention of "a model for text repunctuation and recapitalization", which I wonder if it could be used to break a very long text (eg a book) into pieces that can be digested by the tts engine (link: https://habr.com/ru/post/581960/)
- as mentioned in another post, if you want a simple 'convert_this_text_file' CLI utility, you'll have to roll your own or use https://github.com/Grumbel/silero-test/blob/master/silero-te...
Altogether very nice work, especially the speed.