Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
jhansss
/
SingingSDS
like
0
Running
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
bb840e1
SingingSDS
6.04 MB
9 contributors
History:
68 commits
jhansss
Update LLM model to Gemini 2.5 Flash by default
bb840e1
5 months ago
assets
refactor init
5 months ago
characters
Rename timbre to voice; add speaker parameters to SVS modules
5 months ago
config
Update LLM model to Gemini 2.5 Flash by default
5 months ago
data
Add more synthesized melodies from Wenhao, and update genre handler to load both datasets
5 months ago
data_handlers
Add more synthesized melodies from Wenhao, and update genre handler to load both datasets
5 months ago
evaluation
commit
5 months ago
modules
Fix Gemini LLM implementation and imports
5 months ago
resources
refactor init
5 months ago
tests
Fix Gemini LLM implementation and imports
5 months ago
.gitattributes
Safe
168 Bytes
Track audio files with Git LFS
5 months ago
.gitignore
Safe
14 Bytes
unify configs & add readme
8 months ago
README.md
4.2 kB
bug fixed
5 months ago
app.py
275 Bytes
Add CLI functionality and restructure configuration files
5 months ago
cli.py
1.39 kB
support output file path in pipeline.py
5 months ago
interface.py
9.79 kB
support output file path in pipeline.py
5 months ago
pipeline.py
4.24 kB
support output file path in pipeline.py
5 months ago
requirements.txt
288 Bytes
Add Gemini
5 months ago
