Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
jhansss
/
SingingSDS
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
SingingSDS
Ctrl+K
Ctrl+K
9 contributors
History:
128 commits
jhansss
Updated character prompt
16346b5
about 1 month ago
assets
Update Yaoyin's character image
about 1 month ago
characters
Updated character prompt
about 1 month ago
config
change bilingual svs to use espnet/mixdata_svs_visinger2_spkemb_lang_pretrained_avg
about 1 month ago
data
Add more synthesized melodies from Wenhao, and update genre handler to load both datasets
about 1 month ago
data_handlers
Add more synthesized melodies from Wenhao, and update genre handler to load both datasets
about 1 month ago
evaluation
change bilingual svs to use espnet/mixdata_svs_visinger2_spkemb_lang_pretrained_avg
about 1 month ago
modules
Add more iterations to prompt gemini
about 1 month ago
resources
refactor init
about 2 months ago
tests
add more llms; add system prompt support; add device=auto
about 1 month ago
.gitattributes
Safe
168 Bytes
Track audio files with Git LFS
about 1 month ago
.gitignore
Safe
14 Bytes
unify configs & add readme
5 months ago
README.md
Safe
4.36 kB
Merge branch 'refactor' into hf
about 1 month ago
app.py
Safe
386 Bytes
Merge branch 'refactor' into hf
about 1 month ago
cli.py
Safe
2.68 kB
Refactor CLI to support multiple query audio inputs
about 1 month ago
interface.py
Safe
9.9 kB
update PER placeholder
about 1 month ago
pipeline.py
Safe
4.63 kB
increase max_sentences from 2 to 5 for improved response generation.
about 1 month ago
requirements.txt
Safe
445 Bytes
specify basic-pitch version to 0.4.0 in requirements.txt
about 1 month ago