-
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
Slimmer Computed Latents: falls back to the original, 12.9KiB way of storing latents (without the extra bits required for using the CVVP model).
Disable the setting.
I haven't gotten around to documenting it, but per commit 3899f9b4e3d70e18ec11602f33e8c75e767ee0e6:
added (yet another) experimental voice latent calculation mode (when chunk size is 0 and…
fe8bf7a9d1
added helper script to cull short enough lines from training set as a validation set (if it yields good results doing validation during training, i'll add it to the web ui)
Per the wiki:
This will update the graph below with the current loss rate. This is useful to see how "ready" your…
Per mrq/ai-voice-cloning#87, it's not a good idea to blindly increase it, as longer sentences will break it.
Reverted in mrq/tortoise-tts commit 3dd5cad324.
In the future, if it does happen again, you'll need to lower the…
3dd5cad324
reverting additional auto-suggested batch sizes, per mrq/ai-voice-cloning#87 proving it in fact, is not a good idea
3dd5cad324
reverting additional auto-suggested batch sizes, per mrq/ai-voice-cloning#87 proving it in fact, is not a good idea
Go under settings and set Sample Batch Size to 16. If you updated mrq/tortoise-tts recently, it added an additional automatic batch size tier, that I suppose isn't actually safe to use for…
Implemented an override in commit 7f89e8058acfea272e5e0b9fef784e1efa8d958b. Cannot validate, but I'm sure it's working.