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#80 2023-03-07 13:24:24 +00:00
CVVP latents missing

Per the wiki:

Slimmer Computed Latents: falls back to the original, 12.9KiB way of storing latents (without the extra…

ecker closed issue ecker/ai-voice-cloning#80 2023-03-07 13:24:24 +00:00
CVVP latents missing
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 05:43:30 +00:00
df5ba634c0 brain dead
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 05:35:30 +00:00
2726d98ee1 fried my brain trying to nail out bugs involving using solely ar model=auto
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 04:34:52 +00:00
d7a5ad9fd9 cleaned up some model loading logic, added 'auto' mode for AR model (deduced by current voice)
ecker pushed to main at ecker/tortoise-tts 2023-03-07 04:34:05 +00:00
26133c2031 do not reload AR/vocoder if already loaded
ecker pushed to master at ecker/tortoise-tts 2023-03-07 04:34:03 +00:00
26133c2031 do not reload AR/vocoder if already loaded
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 03:55:41 +00:00
3899f9b4e3 added (yet another) experimental voice latent calculation mode (when chunk size is 0 and theres a dataset generated, itll leverage it by padding to a common size then computing them, should help avoid splitting mid-phoneme)
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 03:01:07 +00:00
5063728bb0 brain worms and headaches
ecker commented on issue ecker/ai-voice-cloning#69 2023-03-07 02:59:04 +00:00
Just some questions from a newbie...

Is there a rough value I should aim for?

To reiterate from the wiki:

However, there doesn't seem to be a…

ecker commented on issue ecker/ai-voice-cloning#45 2023-03-07 02:50:10 +00:00
Feature Request: Use WhisperX instead of Whisper for preparing dataset

It's implemented, but with headaches.

ecker closed issue ecker/ai-voice-cloning#45 2023-03-07 02:49:55 +00:00
Feature Request: Use WhisperX instead of Whisper for preparing dataset
ecker closed issue ecker/ai-voice-cloning#72 2023-03-07 02:49:46 +00:00
Great job!
ecker closed issue ecker/ai-voice-cloning#71 2023-03-07 02:49:26 +00:00
Specific wav file format?
ecker closed issue ecker/ai-voice-cloning#75 2023-03-07 02:49:15 +00:00
start.bat
ecker commented on issue ecker/ai-voice-cloning#77 2023-03-07 02:48:37 +00:00
Collab Notebook Training - issue

The dvae.pth required for training will download when running training. I still don't understand how you managed to brick your colab install, and I honestly don't have the time right now to…

ecker closed issue ecker/ai-voice-cloning#77 2023-03-07 02:48:37 +00:00
Collab Notebook Training - issue
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 02:47:13 +00:00
0f31c34120 download dvae.pth for the people who managed to somehow put the web UI into a state where it never initializes TTS at all somehow
ecker pushed to master at ecker/ai-voice-cloning 2023-03-07 02:45:31 +00:00
0f0b394445 moved (actually not working) setting to use BigVGAN to a dropdown to select between vocoders (for when slotting in future ones), and ability to load a new vocoder while TTS is loaded
ecker pushed to main at ecker/tortoise-tts 2023-03-07 02:44:23 +00:00
e2db36af60 added loading vocoders on the fly