8k lines, one clip per line, 8k clips.
お兄ちゃん、大きすぎる!
What settings are you using in "Prepare Dataset" so that you don't have to check and fix each clip manually? How…
- batch one didn't trim clips that exceeded 11.6s (dataset size of ~8k, for ~15 epochs)
Hold up, by "dataset size of ~8k" do you mean train.txt was ~8kb or ~8k clips?
For new languages, you'll want to increase the text LR ratio to 1, as you're effectively re-teaching the model a new language (or specifically, a new sequence of phonemes to expect).
Does…
Can confirm latest commit is broken on Windows but working on faux Linux (WSL2 on Win10).
Another minor thing: "Reset do Default" always causes an error:
Traceback (most recent call last):
File "/home/sneed/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/blocks.p…Allegedly WSL2 does support nccl, per NVIDIA's doc/blog/guide. I'm not too well-versed in how robust WSL2 is, but I imagine just using…
Ahh, bugger. I could swear I saw a performance boost but it must have been from offloading everything else I was doing to the other GPU.
Will try in WSL, thanks!
Seems to have broken multi-GPU training on Windows
To be technical, there never was. I'll never be able to validate it myself for Windows, as my GPUs are two 6800XTs and a 2060.
…