ecker
18 Followers · 0 Following

  • 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
Repositories
10
 Projects Packages Public Activity Starred Repositories
ecker commented on issue ecker/ai-voice-cloning#149 2023-03-17 18:57:58 +00:00
"Validate Training Configuration" isn't showing console output any more

Fixed in commit f34cc382c5b785dbf4565e509cbc75462447d72c.

ecker closed issue ecker/ai-voice-cloning#149 2023-03-17 18:57:58 +00:00
"Validate Training Configuration" isn't showing console output any more
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 18:57:44 +00:00
f34cc382c5 yammed
ecker commented on issue ecker/ai-voice-cloning#147 2023-03-17 18:40:54 +00:00
Discussion about Fine Tuning on a different language.

Did you convert all the Kanji in your training set to Hiragana beforehand or leave as is?

My naivety left it in as-is, and had whatever DLAS/tortoise uses handle it (which seem to be…

ecker commented on issue ecker/ai-voice-cloning#147 2023-03-17 14:47:42 +00:00
Discussion about Fine Tuning on a different language.

I've read that it's possible with other languages.

Yeah, there's a French model floating around, which I'm surprised as it was one of the earlier finetunes I've seen. I can't vouch for how…

ecker commented on issue ecker/ai-voice-cloning#145 2023-03-17 13:08:53 +00:00
Utilities>Tokenizer does not work after TTS is loaded

Should be fixed in commit 96b7f9d2cc857b72f4a7de5ebb1875b140d272f8.

ecker closed issue ecker/ai-voice-cloning#145 2023-03-17 13:08:53 +00:00
Utilities>Tokenizer does not work after TTS is loaded
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 13:08:41 +00:00
96b7f9d2cc yammed
ecker commented on issue ecker/ai-voice-cloning#148 2023-03-17 13:07:51 +00:00
Errors on training : AttributeError: module 'torch._C' has no attribute '_cuda_setDevice'

You need to pass --force-reinstall when trying to install torch again.

ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 05:33:58 +00:00
249c6019af cleanup, metrics are grabbed for vall-e trainer
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 05:23:29 +00:00
906cde72c7 hide unused training config options that only are for DLAS
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 05:12:03 +00:00
7e23c31aea ops
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 05:00:49 +00:00
01f71754eb ops
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 04:54:07 +00:00
e624473aaa cleanup, metrics are grabbed for vall-e trainer
ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 02:08:17 +00:00
1b72d0bba0 forgot to separate phonemes by spaces for [redacted]
ecker commented on issue ecker/ai-voice-cloning#133 2023-03-17 01:28:06 +00:00
Mispronouncing certain letters for slavic languages

phonemes = phonemize(text,language=lang,strip=True,preserve_punctuation=True, with_stress=True, backend='espeak')

Added.

Also it would be nice to have aditional param like backend so…

ecker pushed to master at ecker/ai-voice-cloning 2023-03-17 01:24:18 +00:00
d4c50967a6 cleaned up some prepare dataset code
ecker pushed to master at ecker/ai-voice-cloning 2023-03-16 20:48:51 +00:00
0b62ccc112 setup bnb on windows as needed
ecker pushed to master at ecker/DL-Art-School 2023-03-16 20:48:23 +00:00
7b5e0592f8 migrated bitsandbytes out, since AIVC technically uses this more
ecker pushed to master at ecker/ai-voice-cloning 2023-03-16 20:48:18 +00:00