JunseokOh

Also there is about 400 utterance for each speaker At make_metadata.py code, to use all data, i replace https://github.com/auspicious3000/autovc/blob/79dda70cff8e4e15e634f64dd7364c6a090b799b/make_metadata.py#L42-L47 to `melsp = torch.from_numpy(tmp[np.newaxis, :, :]).cuda()`

 I guess there is another typo in appendix. In equation (18) and (19) when replcae E^*(x) by minimum value, the location of 0 and m should be changed.

I have the sam question. When I campare equation of deterministic DDIM sampling in the Null-text Inversion paper, it is different with DDIM & DiffuisonCLIP & Diffusion models beat GAN...

Results for bohemina. Also there is few artifact, and result for SPE have changed color