mrq/ai-voice-cloning
31
74
Fork 43
Code Issues 223 Pull Requests 5 Packages Projects Releases Wiki Activity
Collection of utilities aimed to voice clone through AI
164 Commits 1 Branch 0 Tags 12 MiB
Python 91.1%
Jupyter Notebook 4.9%
Shell 2.1%
Batchfile 1.1%
Dockerfile 0.8%
b4098dca73
Go to file
mrq b4098dca73 made validation working (will document later)
2023-03-08 02:58:00 +00:00
bin
config just in case 2023-02-17 20:13:00 +00:00
dlas@6eb7ebf847 oops v2 2023-03-05 14:19:41 +00:00
models made validation working (will document later) 2023-03-08 02:58:00 +00:00
results
src made validation working (will document later) 2023-03-08 02:58:00 +00:00
tortoise-tts@cc36c0997c added update checking for dlas and tortoise-tts, caching voices (for a given model and voice name) so random latents will remain the same 2023-03-07 17:04:45 +00:00
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 +00:00
voices
.gitignore experimental multi-gpu training (Linux only, because I can't into batch files) 2023-03-03 04:37:18 +00:00
.gitmodules I forgot submodules existed 2023-02-19 21:41:51 +00:00
LICENSE
notebook.ipynb oops 2023-02-24 16:23:30 +00:00
README.md huge success 2023-02-23 06:24:54 +00:00
requirements.txt added api_name for generation, added whisperx backend, relocated use whispercpp option to whisper backend list 2023-03-06 05:21:33 +00:00
setup-cuda.bat forgot to reorder the dependency install because whisperx needs to be installed before DLAS 2023-03-06 16:43:17 +00:00
setup-cuda.sh forgot to reorder the dependency install because whisperx needs to be installed before DLAS 2023-03-06 16:43:17 +00:00
setup-directml.bat forgot to reorder the dependency install because whisperx needs to be installed before DLAS 2023-03-06 16:43:17 +00:00
setup-rocm-bnb.sh added setup script for bitsandbytes-rocm (soon: multi-gpu testing, because I am finally making use of my mispurchased second 6800XT) 2023-03-03 02:58:34 +00:00
setup-rocm.sh forgot to reorder the dependency install because whisperx needs to be installed before DLAS 2023-03-06 16:43:17 +00:00
start.bat added button to just load a training set's loss information, added installing broncotc/bitsandbytes-rocm when running setup-rocm.sh 2023-03-02 01:35:12 +00:00
start.sh I swear I committed forwarding arguments from the start scripts 2023-02-19 15:01:16 +00:00
train.bat added button to just load a training set's loss information, added installing broncotc/bitsandbytes-rocm when running setup-rocm.sh 2023-03-02 01:35:12 +00:00
train.sh use torchrun instead for multigpu 2023-03-04 20:53:00 +00:00
update-force.bat one more 2023-03-06 16:47:34 +00:00
update-force.sh one more 2023-03-06 16:47:34 +00:00
update.bat added button to just load a training set's loss information, added installing broncotc/bitsandbytes-rocm when running setup-rocm.sh 2023-03-02 01:35:12 +00:00
update.sh added api_name for generation, added whisperx backend, relocated use whispercpp option to whisper backend list 2023-03-06 05:21:33 +00:00

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.