-
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
The enhuiz implementation seems dead, the author is unresponsive
I'm no stranger to that, given how I'm pretty much fostering TorToiSe, whether I like it or not.
and going by the open…
Since the CLVP step is pretty fast already, would it be possible to have an option to change the batch size of only the autoregressive model?
Not possible, they go hand and hand.
…
Was it with VALL-E or DLAS?
DLAS.
What effect does "language": "ja", in the japanese.json have?
Hints to both DLAS's [tokenizer](https://git.ecker.tech/mrq/DL-Art-School/src/branch/mas…
Trained a new model with the Japanese tokenizer, and after ~55 epochs (~825000 samples processed),…
Not possible, as the CVVP requires auto_conds from processing the original audio. Random voices never possessed…
My batch size is pretty much pinned to 16 for my 2x6800XTs (2x16GiB) if I want stability. Granted, distributed training is different from DLAS, where DLAS will take your batch size and divide by…
Do the "Prompt Engineering" options still work with the Japanese model
I don't know, and desu I don't care too much to find out if it does.
From a [cursory auditing](https://github.com/neon…
Line splitting Works on my Machine™.
Phonemizer message should be gone.