ethanfel
/
ai-voice-cloning
forked from mrq/ai-voice-cloning
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Collection of utilities aimed to voice clone through AI
105 Commits
1 Branch
0 Tags
559 KiB
Python 88.4%
Jupyter Notebook 7.5%
Shell 2.4%
Batchfile 1.7%
 
 
 
 
Go to file
mrq 534a761e49 added loading/saving of voice latents by model hash, so no more needing to manually regenerate every time you change models 2023-03-02 00:46:52 +07:00
bin Initial refractor 2023-02-17 00:08:27 +07:00
config just in case 2023-02-17 20:13:00 +07:00
dlas@0f04206aa2 fixed some files not copying for bitsandbytes (I was wrong to assume it copied folders too), fixed stopping generating and training, some other thing that I forgot since it's been slowly worked on in my small free times 2023-02-24 23:13:13 +07:00
models added new training tunable: loss_text_ce_loss weight, added option to specify source model in case you want to finetune a finetuned model (for example, train a Japanese finetune on a large dataset, then finetune for a specific voice, need to truly validate if it produces usable output), some bug fixes that came up for some reason now and not earlier 2023-03-01 01:17:38 +07:00
results Initial refractor 2023-02-17 00:08:27 +07:00
src added loading/saving of voice latents by model hash, so no more needing to manually regenerate every time you change models 2023-03-02 00:46:52 +07:00
tortoise-tts@7cc0250a1a fixed some files not copying for bitsandbytes (I was wrong to assume it copied folders too), fixed stopping generating and training, some other thing that I forgot since it's been slowly worked on in my small free times 2023-02-24 23:13:13 +07:00
training 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. 2023-02-18 02:07:22 +07:00
voices Initial refractor 2023-02-17 00:08:27 +07:00
.gitignore Initial refractor 2023-02-17 00:08:27 +07:00
.gitmodules I forgot submodules existed 2023-02-19 21:41:51 +07:00
LICENSE Initial refractor 2023-02-17 00:08:27 +07:00
README.md huge success 2023-02-23 06:24:54 +07:00
notebook.ipynb oops 2023-02-24 16:23:30 +07:00
requirements.txt changed setup scripts to just clone mrq/tortoise-tts and install locally, instead of relying on pip's garbage git-integrations 2023-02-19 05:29:01 +07:00
setup-cuda.bat compat with python3.10+ finally (and maybe a small perf uplift with using cu117) 2023-02-26 17:46:57 +07:00
setup-cuda.sh removed the logic to toggle BNB capabilities, since I guess I can't do that from outside the module 2023-02-23 07:05:39 +07:00
setup-directml.bat removed the logic to toggle BNB capabilities, since I guess I can't do that from outside the module 2023-02-23 07:05:39 +07:00
setup-rocm.sh removed the logic to toggle BNB capabilities, since I guess I can't do that from outside the module 2023-02-23 07:05:39 +07:00
start.bat I swear I committed forwarding arguments from the start scripts 2023-02-19 15:01:16 +07:00
start.sh I swear I committed forwarding arguments from the start scripts 2023-02-19 15:01:16 +07:00
train.bat 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. 2023-02-18 02:07:22 +07:00
train.sh crunchbangs 2023-02-18 02:46:44 +07:00
update-force.bat crunchbangs 2023-02-18 02:46:44 +07:00
update-force.sh crunchbangs 2023-02-18 02:46:44 +07:00
update.bat huge success 2023-02-23 06:24:54 +07:00
update.sh huge success 2023-02-23 06:24:54 +07:00

README.md

AI Voice Cloning

This repo/rentry aims to serve as both a foolproof guide for setting up AI voice cloning tools for legitimate, local use on Windows/Linux, as well as a stepping stone for anons that genuinely want to play around with TorToiSe.

Similar to my own findings for Stable Diffusion image generation, this rentry may appear a little disheveled as I note my new findings with TorToiSe. Please keep this in mind if the guide seems to shift a bit or sound confusing.

>Ugh... why bother when I can just abuse 11.AI?

You're more than welcome to, but TorToiSe is shaping up to be a very promising tool, especially with finetuning now on the horizon.

This is not endorsed by neonbjb. I do not expect this to run into any ethical issues, as it seems (like me), this is mostly for making funny haha vidya characters say funny lines.

Documentation

Please consult the wiki for the documentation, including how to install, prepare voices for, and use the software.

Bug Reporting

If you run into any problems, please refer to the issues you may encounter wiki page first. Please don't hesitate to submit an issue.

Changelogs

Below will be a rather-loose changelogss, as I don't think I have a way to chronicle them outside of commit messages:

2023.02.22

  • greatly reduced VRAM consumption through the use of TimDettmers/bitsandbytes
  • cleaned up section of code that handled parsing output from training script
  • added button to reconnect to the training script's output (sometimes skips a line to update, but it's better than nothing)
  • actually update submodules from the update script (somehow forgot to pass --remote)

Before 2023.02.22

Refer to commit logs.