• 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
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 16:30:07 +00:00
8d268bc7a3 training added, seems to work, need to test it more
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 15:53:58 +00:00
229be0bdb8 almost
ecker pushed to master at ecker/DL-Art-School 2023-02-17 15:48:04 +00:00
a09cf98c7f more cleanup, pip-ifying won't work, got an alternative
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 13:57:24 +00:00
f87764e7d0 Slight fix, getting close to be able to train from the web UI directly
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 06:25:40 +00:00
8482131e10 oops x2
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 06:11:13 +00:00
a16e6b150f oops
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 06:01:25 +00:00
12933cfd60 added dropdown to select which whisper model to use for transcription, added note that FFMPEG is required
ecker commented on issue ecker/ai-voice-cloning#1 2023-02-17 05:46:10 +00:00
Import error: Failed to load PyTorch C Extensions

Couldn't replicate, although I did find it was bitching at me for not having psutil installed.

ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 05:43:03 +00:00
96e9acdeec added preparation of LJSpeech-esque dataset
ecker pushed to main at ecker/tortoise-tts 2023-02-17 04:50:08 +00:00
ac0a572679 arg to skip voice latents for grabbing voice lists (for preparing datasets)
ecker commented on issue ecker/ai-voice-cloning#1 2023-02-17 04:34:26 +00:00
Import error: Failed to load PyTorch C Extensions

Strange, I'll see if I can replicate it. I admittedly haven't tested setting up from a clean slate after cleanup, so I'll pick at it when I get a chance.

For the meantime, you can copy-paste…

ecker pushed to master at ecker/DL-Art-School 2023-02-17 04:08:35 +00:00
6afa2c299e break if your dataset size is smaller than your batch size
ecker commented on issue ecker/tortoise-tts#39 2023-02-17 03:32:01 +00:00
activate.bat missing

Fixed in commit b2dd5e31a8f76d4f8b51ae5a92175891c06afccc.

Again, in the middle of refractoring.

ecker pushed to main at ecker/tortoise-tts 2023-02-17 03:31:37 +00:00
b2dd5e31a8 updated notebooks to use the new "main" setup
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 03:31:00 +00:00
9c0e4666d2 updated notebooks to use the new "main" setup
ecker pushed to master at ecker/ai-voice-cloning 2023-02-17 03:05:48 +00:00
f8249aa826 tab to generate the training YAML
ecker pushed to master at ecker/DL-Art-School 2023-02-17 02:03:46 +00:00
94d0f16608 Necessary fixes to get it to work
ecker pushed to main at ecker/tortoise-tts 2023-02-17 01:46:49 +00:00
4d9ba00dcc oops
ecker pushed to master at ecker/DL-Art-School 2023-02-17 00:34:14 +00:00
49e23b226b pip-ify