Rolun
Rolun
@suzhenghang Great point! I ran some tests to see the impact of the faiss index on the different models. Seems like you are right, and I found some other interesting...
Update: I re-initialized the emb_g layer and set it to only have 2 speakers, redid the fine-tuning and now it works great :) I also misspoke in my last comment...
@yaodada1 RVC does not support multi-training natively. What worked for me was to set `hps.model.spk_embed_dim` to number of speakers (4 in your case) and then replace the `emb_g.weight` with a...
@yaodada1 Great to hear! :)
@ms903x1 - thanks! So by the sounds of it, there doesn't need to be mute wav files for each speaker (or at all for longer datasets), just a couple in...
@RVC-Boss I've only seen the 110 speaker version so far, do you have a link to the 108 version?