Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Wismut
/
StyleTTS2_Studio
like
16
Running
App
Files
Files
Community
1
Fetching metadata from the HF Docker repository...
main
StyleTTS2_Studio
148 MB
1 contributor
History:
14 commits
This space has 1 file scanned as unsafe.
Show
files
Wismut
fixed saved voice persistence on reload
4d3cdf4
12 months ago
Modules
initial commit
about 1 year ago
Utils
initial commit
about 1 year ago
pca
initial commit
about 1 year ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
.gitignore
319 Bytes
initial commit
about 1 year ago
Logo.ai
1.24 MB
fixed missing cuda option
about 1 year ago
Logo.png
53.7 kB
fixed missing cuda option
about 1 year ago
README.md
1.48 kB
initial commit
about 1 year ago
annotated_features.npy
2.58 kB
xet
initial commit
about 1 year ago
app.py
19 kB
fixed saved voice persistence on reload
12 months ago
inference.py
10.5 kB
switched to openphonemizer
about 1 year ago
models.py
22.2 kB
initial commit
about 1 year ago
packages.txt
0 Bytes
switched to openphonemizer
about 1 year ago
pca_model.pkl
8.18 kB
xet
initial commit
about 1 year ago
pyproject.toml
750 Bytes
switched to openphonemizer
about 1 year ago
requirements.txt
343 Bytes
remove torch from requirements.txt for pinokio
about 1 year ago
text2speech.py
21.2 kB
fixed missing cuda option
about 1 year ago
uv.lock
441 kB
switched to openphonemizer
about 1 year ago
voices.json
71.8 kB
fixed saved voice persistence on reload
12 months ago
voices_.json.example
71.8 kB
initial commit
about 1 year ago