Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
dkounadis
/
artificial-styletts2
like
9
Text-to-Audio
Audiocraft
English
audiogen
styletts2
shift-tts
sound
audio-generation
text-to-speech
mimic3
License:
cc-by-nc-sa-4.0
Model card
Files
Files and versions
xet
Community
4
Use this model
e83a997
artificial-styletts2
/
audiocraft
Ctrl+K
Ctrl+K
3 contributors
History:
18 commits
This model has 2 files scanned as unsafe.
Show
files
Dionyssos
DEBUG steaming past key changes 47x during next token calc
e83a997
10 months ago
utils
revert transformer.py
10 months ago
__init__.py
Safe
0 Bytes
fx
10 months ago
activations.py
Safe
3.27 kB
audiocraft
11 months ago
audiogen.py
7.25 kB
DEBUG: cross_attention_src = query or key?
10 months ago
builders.py
6.89 kB
duplicate xN_DRAW - for long gen
10 months ago
codebooks_patterns.py
Safe
14.4 kB
duplicate xN_DRAW - for long gen
10 months ago
conditioners.py
13.2 kB
DEBUG: cross_attention_src = query or key?
10 months ago
conv.py
Safe
9.34 kB
fx
10 months ago
diffusion_schedule.py
Safe
12 kB
audiocraft
11 months ago
encodec.py
Safe
2.73 kB
duplicate xN_DRAW - for long gen
10 months ago
lm.py
16.6 kB
DEBUG steaming past key changes 47x during next token calc
10 months ago
loaders.py
6.8 kB
duplicate xN_DRAW - for long gen
10 months ago
lstm.py
Safe
759 Bytes
audiocraft
11 months ago
rope.py
Safe
5.65 kB
audiocraft
11 months ago
seanet.py
7.19 kB
fx
10 months ago
transformer.py
20.8 kB
DEBUG steaming past key changes 47x during next token calc
10 months ago
unet.py
8.32 kB
audiocraft
11 months ago
vq.py
Safe
8.76 kB
index out of bounds 2048 @ dequantize()
10 months ago
