Spaces:

espnet
/

SingingSDS

Runtime error

App Files Files Community

6.4 MB

Ctrl+K

Ctrl+K

9 contributors

History: 116 commits

jhansss's picture

increase gemini max_output_tokens

55bdc43 10 months ago

assets
Update Yaoyin's character image 10 months ago
characters
update configurations, including Yaoyin character prompt, default setup, svs model choices 10 months ago
config
update configurations, including Yaoyin character prompt, default setup, svs model choices 10 months ago
data
Add more synthesized melodies from Wenhao, and update genre handler to load both datasets 10 months ago
data_handlers
change kising dataset source to public dataset 10 months ago
evaluation
update configurations, including Yaoyin character prompt, default setup, svs model choices 10 months ago
modules
increase gemini max_output_tokens 10 months ago
resources
refactor init 10 months ago
tests
add more llms; add system prompt support; add device=auto 10 months ago
.gitattributes

168 Bytes
Track audio files with Git LFS 10 months ago
.gitignore

14 Bytes
unify configs & add readme about 1 year ago
README.md

3.33 kB
update configurations, including Yaoyin character prompt, default setup, svs model choices 10 months ago
app.py

386 Bytes
Merge branch 'refactor' into hf 10 months ago
cli.py

2.68 kB
Refactor CLI to support multiple query audio inputs 10 months ago
interface.py

9.96 kB
update configurations, including Yaoyin character prompt, default setup, svs model choices 10 months ago
pipeline.py

4.63 kB
increase max_sentences from 2 to 5 for improved response generation. 10 months ago
requirements.txt

427 Bytes
remove tensorflow from requirements.txt 10 months ago