Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
stepfun-ai
/
Step-Audio-EditX
like
92
Running
on
Zero
App
Files
Files
Community
3
Fetching metadata from the HF Docker repository...
0dc7005
Step-Audio-EditX
5.31 MB
4 contributors
History:
14 commits
xieli
feat: support int4/int8 quantization when load
0dc7005
about 1 month ago
config
feat: fix paralinguistic, clone prompt, style prompt, input limit
about 1 month ago
funasr_detach
audio edit
about 2 months ago
stepvocoder
feat: update hifigan
about 1 month ago
.gitattributes
240 Bytes
audio edit
about 2 months ago
.gitignore
20 Bytes
audio edit
about 2 months ago
LICENSE
11.4 kB
Initial commit
about 2 months ago
README.md
277 Bytes
feat: support int4/int8 quantization when load
about 1 month ago
__init__.py
0 Bytes
audio edit
about 2 months ago
app.py
23.6 kB
feat: support int4/int8 quantization when load
about 1 month ago
model_loader.py
16.3 kB
feat: support int4/int8 quantization when load
about 1 month ago
requirements.txt
413 Bytes
feat: support int4/int8 quantization when load
about 1 month ago
tokenizer.py
8.23 kB
audio edit
about 2 months ago
tts.py
15.1 kB
feat: support int4/int8 quantization when load
about 1 month ago
utils.py
6.51 kB
audio edit
about 2 months ago
