Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
WeReCooking
/
ACE-Step-CPU
like
1
Running
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
059d153
ACE-Step-CPU
204 kB
Ctrl+K
Ctrl+K
1 contributor
History:
105 commits
Nekochu
instant cancel during preprocessing (dont wait for thread to finish)
059d153
23 days ago
.dockerignore
69 Bytes
switch to acestep.cpp GGUF: XL turbo Q4_K_M + 4B LM Q5_K_M
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
Dockerfile
4.13 kB
upgrade torch>=2.6 (CLAP needs torch.load fix for CVE-2025-32434)
23 days ago
README.md
4.68 kB
update README with final state, full pipeline inference, LM generation step
29 days ago
app.py
46.1 kB
instant cancel during preprocessing (dont wait for thread to finish)
23 days ago
caption_fast.py
8.47 kB
fix: use librosa instead of torchaudio for VAD (torchcodec not installed), fix audios deprecation
23 days ago
requirements.txt
319 Bytes
add torchcodec for training audio loading
about 1 month ago
start.sh
733 Bytes
switch to acestep.cpp GGUF: XL turbo Q4_K_M + 4B LM Q5_K_M
about 1 month ago
train_engine.py
138 kB
random 60s crop at training time (matches Side-Step chunk-duration), remove pre-split chunking
24 days ago