Collection of utilities aimed to voice clone through AI
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
ben_mkiv 26d9f7df88 added simple websocket server which allows to start tts generation tasks, retrieving autoregressive models and voices list 6 months ago
bin Initial refractor 1 year ago
models remove redundant phonemize for vall-e (oops), quantize all files and then phonemize all files for cope optimization, load alignment model once instead of for every transcription (speedup with whisperx) 11 months ago
modules added checkboxes to use the original method for calculating latents (ignores the voice chunk field) 9 months ago
results Initial refractor 1 year ago
src added simple websocket server which allows to start tts generation tasks, retrieving autoregressive models and voices list 6 months ago
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. 1 year ago
voices Initial refractor 1 year ago
.dockerignore docker support 11 months ago
.gitignore experimental multi-gpu training (Linux only, because I can't into batch files) 12 months ago
.gitmodules while I'm breaking things, migrating dependencies to modules folder for tidiness 12 months ago
Dockerfile docker: add ffmpeg for whisper and general cleanup 11 months ago
LICENSE Initial refractor 1 year ago
README.md Update 'README.md' 7 months ago
notebook_colab.ipynb share if you 12 months ago
notebook_paperspace.ipynb fixed notebooks, provided paperspace notebook 12 months ago
requirements.txt Freeze pydantic package to 1.10.11 8 months ago
setup-cuda-bnb.bat setup bnb on windows as needed 11 months ago
setup-cuda.bat DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) 11 months ago
setup-cuda.sh DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) 11 months ago
setup-directml.bat updated setup-directml.bat to not hard require torch version because it's updated to torch2 now 10 months ago
setup-docker.sh docker support 11 months ago
setup-rocm-bnb.sh while I'm breaking things, migrating dependencies to modules folder for tidiness 12 months ago
setup-rocm.sh DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) 11 months ago
start-docker.sh docker support 11 months ago
start.bat added PYTHONUTF8 to start/train bats 12 months ago
start.sh :) 12 months ago
train-docker.sh docker: add training script 11 months ago
train.bat ;) 12 months ago
train.sh ;) 12 months ago
update-force.bat removed the hotfix pip installs that whisperx requires now that whisperx is gone 12 months ago
update-force.sh DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) 11 months ago
update.bat added button to just load a training set's loss information, added installing broncotc/bitsandbytes-rocm when running setup-rocm.sh 12 months ago
update.sh added PYTHONUTF8 to start/train bats 12 months ago

README.md

AI Voice Cloning

This repo has been cloned from: https://git.ecker.tech/mrq/ai-voice-cloning

Documentation

Please consult the wiki for the documentation.

Bug Reporting

If you run into any problems, please refer to the Issues You May Encounter wiki page first.