-
https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.
XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG
- Joined on
2022-10-10
Right, some installs will not have python as an alias. I'll push a fix out, although I swore I did this already before, but it might have gotten reverted during migration from the old repo.
As I mentioned in mrq/ai-voice-cloning#17 (comment), I added an experimental way to train fully at half-precision that will convert the original model to one…
I've added/exposed a very experimental training setting: Half Precision in commit 8a1a48f31e30957196213a193c9aab45f1c25520. It'll convert the original training model to float16 and enable…
I tried again on an RTX4000 (8GiB VRAM) with:
- half-precision training
- experimental half-precision training model
- batch size 1 (which surprisingly works)
- mega batch factor 1 (changing…
8a1a48f31e
Added very experimental float16 training for cards with not enough VRAM (10GiB and below, maybe) \!NOTE\! this is VERY EXPERIMETNAL, I have zero free time to validate it right now, I'll do it later
Haven't tested (for reasons), but it should be remedied in commit ed2cf9f5ee558c5efb63b17025ae0b25a29bbaa0.
I guess even 3080s can't train it, as there's another user that can't train off a 3080 either.
I'll cobble together a way to load and finetune it as float16 and see if that gets VRAM consumption…
Almost forgot the venv. Should be as easy as deleting your old one and dropping this in place.
I might have to download a Linux distro and test it…
Took a small bit of elbow grease to get it to work (for simplicity I just thrown it at C:\Tortoise\ai-voice-cloning\ so I don't need to edit some paths, and had to edit .\venv\pyvenv.conf with…
Great idea. In theory, the pieces remain in case I absolutely need to mix and match generations, but I haven't done that at all yet, and worse case I can just open Tenacity and manually edit…
(GPU 0; 10.00 GiB total capacity; 5.88 GiB already allocated; 0 bytes free; 6.06 GiB reserved in total by PyTorch)
Yeah, that doesn't sound right.
Do you already have `Do Not Load TTS On…
I assume training works for AMD on Linux then?
Should be, I haven't tested it, but if it's anything like getting tortoise-tts working under ROCm, it's just as easy as running ./setup-rocm.sh…
Any way you can zip up and send your venv folder? I might be able to figure it out if I can probe the current state.
Windows 10, [...] RX 6900 XTXH
Actually, not to rain on your parade,…
bbc2d26289
I finally figured out how to fix gr.Dropdown.change, so a lot of dumb UI decisions are fixed and makes sense