Skip to content

Fix audio server defaults and CUDA fallback #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Th0rgal wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Fix audio server defaults and CUDA fallback #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
37b5492
Add simple audio server with tool heuristics
Th0rgal Feb 10, 2026
77b1f42
Fix audio server defaults and CUDA fallback
Th0rgal Feb 10, 2026
eaad597
Add FORCE_CPU to bypass CUDA JIT failures
Th0rgal Feb 10, 2026
6163d88
Add GPU compatibility launcher for new CUDA arch
Th0rgal Feb 10, 2026
bb163c4
Fix GPU inference on GB10
Th0rgal Feb 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,3 +69,6 @@ htmlcov/
# Distribution
*.whl


# Server outputs
output_audio/
37 changes: 37 additions & 0 deletions requirements_modified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
# Basic Dependencies
transformers==4.52.3
datasets==3.6.0
numpy<2.0.0
accelerate
deepspeed==0.17.3
librosa

# CV3
conformer==0.3.2
diffusers==0.29.0
gdown==5.1.0
hydra-core==1.3.2
HyperPyYAML==1.2.2
inflect==7.3.1
lightning==2.2.4
loguru
matplotlib==3.7.5
modelscope
networkx==3.1
omegaconf==2.3.0
onnx==1.16.0
openai-whisper
protobuf==4.25
pyarrow==18.1.0
pydantic==2.7.0
pyworld==0.3.4
rich==13.7.1
soundfile==0.12.1
uvicorn==0.30.0
wetext==0.0.4
wget==3.2
x_transformers

# CUDA 13.0 nightly (GB10 / sm_121)
# Install with:
# pip install --pre --index-url https://download.pytorch.org/whl/nightly/cu130 torch torchaudio torchvision
Loading