Spaces:

jailen
/

tortoise-base

Build error

9 contributors

mrq

modified logic to determine valid voice folders, also allows subdirs within the folder (for example: ./voices/SH/james/ will be named SH/james)

faa8da1 almost 2 years ago

bin
Initial refractor almost 2 years 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) almost 2 years ago
modules
a bunch of shit i had uncommited over the past while pertaining to VALL-E almost 2 years ago
results
Initial refractor almost 2 years ago
src
modified logic to determine valid voice folders, also allows subdirs within the folder (for example: ./voices/SH/james/ will be named SH/james) almost 2 years 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. almost 2 years ago
voices
Initial refractor almost 2 years ago
.dockerignore

31 Bytes

docker support almost 2 years ago
.gitignore

1.92 kB

experimental multi-gpu training (Linux only, because I can't into batch files) almost 2 years ago
.gitmodules

191 Bytes

while I'm breaking things, migrating dependencies to modules folder for tidiness almost 2 years ago
Dockerfile

1.47 kB

docker: add ffmpeg for whisper and general cleanup almost 2 years ago
LICENSE

34.7 kB

Initial refractor almost 2 years ago
README.md

1.29 kB

I forgot about the changelog and never kept up with it, so I'll just not use a changelog almost 2 years ago
notebook_colab.ipynb

5.27 kB

share if you almost 2 years ago
notebook_paperspace.ipynb

3.02 kB

fixed notebooks, provided paperspace notebook almost 2 years ago
requirements.txt

118 Bytes

setup bnb on windows as needed almost 2 years ago
setup-cuda-bnb.bat

382 Bytes

setup bnb on windows as needed almost 2 years ago
setup-cuda.bat

585 Bytes

DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) almost 2 years ago
setup-cuda.sh

788 Bytes

DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) almost 2 years ago
setup-directml.bat

512 Bytes

DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) almost 2 years ago
setup-docker.sh

96 Bytes

docker support almost 2 years ago
setup-rocm-bnb.sh

371 Bytes

while I'm breaking things, migrating dependencies to modules folder for tidiness almost 2 years ago
setup-rocm.sh

799 Bytes

DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) almost 2 years ago
start-docker.sh

463 Bytes

docker support almost 2 years ago
start.bat

106 Bytes

added PYTHONUTF8 to start/train bats almost 2 years ago
start.sh

119 Bytes

:) almost 2 years ago
train-docker.sh

646 Bytes

docker: add training script almost 2 years ago
train.bat

104 Bytes

;) almost 2 years ago
train.sh

85 Bytes

;) almost 2 years ago
update-force.bat

414 Bytes

removed the hotfix pip installs that whisperx requires now that whisperx is gone almost 2 years ago
update-force.sh

458 Bytes

DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) almost 2 years ago
update.bat

39 Bytes

added button to just load a training set's loss information, added installing broncotc/bitsandbytes-rocm when running setup-rocm.sh almost 2 years ago
update.sh

220 Bytes

added PYTHONUTF8 to start/train bats almost 2 years ago