Jakub Piotr Cłapa
Jakub Piotr Cłapa
Hey, I implemented the API we talked about. You can now pass a file or URL to the voice sample and it will be used to condition the model: ```...
This is a nice idea. The trick seems to be getting good ground truth emotional speech samples and labels that don't sound fake. This is not currently supported in any...
It’s best if you ask on the LAION Discord (link in the README).
CPU could be supported through whisper.cpp/llama.cpp but we are not working on that right now. MPS should work with minimal tweaks (there may be some hardcoded “cuda” settings).
@fakerybakery You can try and report back how difficult it is :) I don't have this on my roadmap right now (I am mostly focused on improving quality and language...
@BBC-Esq we are using [nbdev](https://nbdev.fast.ai/). it allows you to edit either the notebooks or the `.py` files and later synchronize the changes. I am on holiday next week but afterwards...
Regarding Vocos and MPS maybe it would be worth raising an issue on their GitHub and see what the author says? I was using this model as-is so I am...
The sdp_kernel is kind of important for performance on CUDA so we’d have to figure out how to make them transparent for MPS. Maybe make a new context manager that...
I was thinking about writing to the Vocos author since I believe sometimes the offending operations can be changed to something a little bit different that works out of the...
I think we need native speakers to ensure high quality material and build the best global open source TTS system. I am thinking of setting up a common format and...