-
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
I did a quick train on James Sunderland again, but with the training dataset text as IPA phonemes; it works, to say the least:
- default tokenizer will just convert IPA to english equivalent,…
Seems fine to me. I'm not sure if it has to do with your reported iteration rates being whack.
blah
I did everything under the sun until I copied the DLL to the current working directly and it Just Worked™.
Anyways, the entire experience soured me enough that I'll refuse to…
You know what would make it even better? If tts.get_conditioning_latents() could use multiple GPU's...
A nightmare to think about implementing, and beyond the scope of the matter.
…
As I understand it if I provide my own dataset then I have to provide my own inference model trained on it
No shit. You already need to provide your own model anyways, as there's no publicly…
Even if your validation.txt contains bad transcriptions?
Correct. It's just a way to get a defacto metric against data that's the model is not trained against. Nothing from the validation…
Fixed in mrq/DL-Art-School commit fd375670eb.
This was due to torch2.0.0 silently releasing upstream.