Christopher Aedo

Maybe this has something to do with CUDA, so far I am unable to reproduce. Can you share platform details, as well as the output at the start of the...

I don't see anything obvious going on here unfortunately. Could you try one more thing? Add `--no-deepspeed --debug` to your command and let's see what specific sentence it's failing on,...

If it's not something weird coming from the text itself (like somehow it's trying to pass a special character, or pass an empty string to TTS), I'm not sure what...

@acerbusace can you try what @two-9 suggested and see if that solves it? If it does, I'll update requirements.txt and pin to that version of transformers.

Excellent! Thanks for checking that, and thank you a ton to @two-9 for the fix, probably would have taken me a while to remember to start googling for tensor errors...

Hmm, are you installing in a virtual environment? I just did the following on an M1 macbook pro and there were no issues, maybe try this? (you can skip pyenv...

Nope, that's the same thing, and definitely don't apologize :) I'm happy to help however, and glad you're trying to mess with this since it's not super user friendly. I...

Hmm, this is pretty strange, doing the install in a virtual environment should have cleared the issues. There's a possibility there were things missing from the requirements.txt file in the...

Thanks for following up. Can you try `pip install TTS==0.22.0` in the virtual environment just to see if Coqui-TTS will install on it's own? If that installs on it's own...

There's an existing PR that incorporates MPS (https://github.com/aedocw/epub2tts/pull/181). The last time I tested it there was no notable improvement in speed. If it requires a nightly build of PyTorch that...