p0p
p0p
I found TTS command line interface to be **slightly** _un-intuitive_ ; be it typing complete model names OR re-loading models for every "--text" run even on the same model. On...
- added a self explanatory vits phoneme duration changer. - it can work for any model that uses duration predictor actually. - notebook shows example for a single sentence, but...
continuing where i left earlier, adding some test cases. - to do -> fix test cases to take in mel instead of linear spectrogram (if anywhere)
From the [paper](https://arxiv.org/abs/2210.13432)  https://github.com/lucidrains/x-transformers/blob/90cef69e272f74756a0e5aa1ddd4523c0a23e49a/x_transformers/autoregressive_wrapper.py#L274-L280 I am still trying to understand the code, ``` rand = torch.randn(inp.shape, device = x.device) ---> creates a random array of normal dist number (0,1)...
Hello, @rtqichen shouldn't the partial derivative actually be TOTAL derivative? (arxiv NODE paper, page 14) 
Hello, nice work. I have a question. Q) how about adding an extra loss at the end of generation to match the spk_enc of reference wav and generated wav? Because...
I will try to explain and expand on the cfm paper to best of my knowledge in this thread. It will serve as a rough notes section, add your thoughts...