-
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
2f7d9ab932
disable BNB for inferencing by default because I'm pretty sure it makes zero differences (can be force enabled with env vars if you'r erelying on this for some reason)
2f7d9ab932
disable BNB for inferencing by default because I'm pretty sure it makes zero differences (can be force enabled with env vars if you'r erelying on this for some reason)
Oh my bad, I meant replace that line with the new line for both of them.
1aef128ccb
added config parameter to randomly select between using a random utterance or using the target audio as the input prompt (to goad training better to learning speech synth)
No issues for me running the install .bat on Win10 + python3.10.
The only issue I can think of is if you're using PowerShell, as the venv activation script (.\venv\Scripts\activate.bat) does…
I feel like I managed to mess up a working environment ages ago where it wasn't actually installing the packages to the venv. Whenever I get the chance I'll validate that the procedure still…
The fundamental difference between the two forks that would cause this is in the method of computing a voice's conditional latents. I can't remember how the 152334H fork handles computing its…
Nope, seems I didn't. I backported my wrapper from it instead of relying on brandishing a fork with it.
Should be fixed in commit 99387920e1c3d741a95b2edf823aa3eab95b9d15 (should, I haven't…
I swear I've already committed a fix for it. It might actually only live in mrq/vall-e but I'll double check.
Slight progress report again: things are going swimmingly again. Losses are going down (not as fast as apparent as I wish, but still going down), and accuracies are going up (again, not as fast as…
Finally got off my ass and "fixed" inferencing in my fork. You have two options with using the model you trained:
Using the original implementation
In [./vall-e/vall_e/__main__.py#L27](h…
0e420f63c7
inferencing is fixed (in the sense it reflects how it works during evaluation/validation)
I had a pretty lengthy progress report (despite framing it as brief), but I felt it was much ado about nothing, and might have painted too high of an expectation that I keep forgetting that I make…
AIVC has Bark integration. I don't really need to use any of the forks, as:
- Fictiverse seems to mostly focus on a web UI
- JonathanFly seems to mostly focus on saving randomly generated voices…
3978921e71
forgot to make the transcription tab visible with the bark backend (god the code is a mess now, I'll suck you off if you clean this up for me (not really))