Spaces:

espnet
/

SingingSDS

Running

App Files Files Community

6.4 MB

9 contributors

History: 116 commits

jhansss's picture

increase gemini max_output_tokens

55bdc43 5 months ago

assets
Update Yaoyin's character image 6 months ago
characters
update configurations, including Yaoyin character prompt, default setup, svs model choices 5 months ago
config
update configurations, including Yaoyin character prompt, default setup, svs model choices 5 months ago
data
Add more synthesized melodies from Wenhao, and update genre handler to load both datasets 6 months ago
data_handlers
change kising dataset source to public dataset 5 months ago
evaluation
update configurations, including Yaoyin character prompt, default setup, svs model choices 5 months ago
modules
increase gemini max_output_tokens 5 months ago
resources
refactor init 6 months ago
tests
add more llms; add system prompt support; add device=auto 6 months ago
.gitattributes

168 Bytes

Track audio files with Git LFS 6 months ago
.gitignore

14 Bytes

unify configs & add readme 9 months ago
README.md

3.33 kB

update configurations, including Yaoyin character prompt, default setup, svs model choices 5 months ago
app.py

386 Bytes

Merge branch 'refactor' into hf 6 months ago
cli.py

2.68 kB

Refactor CLI to support multiple query audio inputs 5 months ago
interface.py

9.96 kB

update configurations, including Yaoyin character prompt, default setup, svs model choices 5 months ago
pipeline.py

4.63 kB

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

427 Bytes

remove tensorflow from requirements.txt 6 months ago