Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
ntt123
/
diffusion-speech-360h
like
0
Runtime error
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
diffusion-speech-360h
574 MB
2 contributors
History:
17 commits
ntt123
use fp32
94055f6
about 1 year ago
nltk_data
inference code
about 1 year ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
.python-version
5 Bytes
inference code
about 1 year ago
README.md
218 Bytes
clean up
about 1 year ago
acoustic_model_0140000.pt
535 MB
xet
Upload 2 files
about 1 year ago
app.py
1.72 kB
initialize model on GPU
about 1 year ago
diffusion.py
1.62 kB
add diffusion utils
about 1 year ago
diffusion_utils.py
3.2 kB
add diffusion utils
about 1 year ago
duration_model_0120000.pt
33.2 MB
xet
Upload 2 files
about 1 year ago
gaussian_diffusion.py
36.1 kB
use gpu
about 1 year ago
maps.json
16.3 kB
inference code
about 1 year ago
models.py
17.4 kB
rm unused import
about 1 year ago
pyproject.toml
313 Bytes
use latest torch
about 1 year ago
requirements.txt
63 Bytes
clean up
about 1 year ago
respace.py
5.46 kB
add diffusion utils
about 1 year ago
sample.py
7.5 kB
use fp32
about 1 year ago
synthesize.py
6.56 kB
rm unused import
about 1 year ago
timestep_sampler.py
6.01 kB
add diffusion utils
about 1 year ago
train_acoustic_dit_b.yaml
751 Bytes
inference code
about 1 year ago
train_duration_dit_s.yaml
763 Bytes
inference code
about 1 year ago
uv.lock
153 kB
add diffusion utils
about 1 year ago