• 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
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 13:07:30 +00:00
a9bd17c353 fixes #2
mrq commented on issue mrq/tortoise-tts#30 2023-02-18 04:03:58 +00:00
Implement Training

I should have everything working for training under the new, cleaned up repo. It took a lot of headaches from how many oddball fixes were needed…

mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 03:36:15 +00:00
c26bda4d96 finally can get training to work under the web UI
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 03:31:50 +00:00
809012c84d debugging in colab is pure cock and ball torture because sometimes the files don't actually update when edited, and sometimes they update after I restart the runtime, notebook can't use venv because I can't source it in a subprocess shell call
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 03:29:57 +00:00
59f84baff1 debugging in colab is pure cock and ball torture because sometimes the files don't actually update when edited, and sometimes they update after I restart the runtime, notebook can't use venv because I can't source it in a subprocess shell call
mrq pushed to master at mrq/DL-Art-School 2023-02-18 03:27:20 +00:00
6c284ef8ec oops
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 03:17:53 +00:00
915ab5f65d fixes
mrq pushed to master at mrq/DL-Art-School 2023-02-18 03:16:00 +00:00
8db762fa17 thought I copied this over
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:46:50 +00:00
602d477935 crunchbangs
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:46:06 +00:00
856f7ff130 crunchbangs
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:42:18 +00:00
f5993ab01b crunchbangs
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:40:37 +00:00
650eada8d5 fix spawning training subprocess for unixes
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:38:56 +00:00
ce5fd23be6 fix spawning training subprocess for unixes
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:32:30 +00:00
abfc210f19 fix spawning training subprocess for unixes
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:26:48 +00:00
ab011933c4 fix spawning training subprocess for unixes
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:26:02 +00:00
d7ce961cae fix spawning training subprocess for unixes
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:25:21 +00:00
466f92da79 fix spawning training subprocess for unixes
mrq pushed to master at mrq/ai-voice-cloning 2023-02-18 02:07:44 +00:00
d5c1433268 a bit of UI cleanup, import multiple audio files at once, actually shows progress when importing voices, hides audio metadata / latents if no generated settings are detected, preparing datasets shows its progress, saving a training YAML shows a message when done, training now works within the web UI, training output shows to web UI, provided notebook is cleaned up and uses a venv, etc.
mrq pushed to master at mrq/DL-Art-School 2023-02-18 02:01:24 +00:00
73d9c3bd46 set output folder to be sane with the cwd as a reference point
mrq pushed to master at mrq/DL-Art-School 2023-02-17 20:49:36 +00:00
5ecf7da881 Fix later