Repository Issue Activity (beta)

#12 Still “Status: Pending” on Hugging Face

#104 SAM’s value in this karaoke maker pipeline...

#75 Question masking behaviour and paper/code discreptancy

#102 Where is multi-diffusion implementation? Currently repo is really weak

#103 Meaning of zeros in the align inputs?

#101 trying the sample code on linux, dependencies cause issue.

#87 sam-audio-judge sam_audio branch still has mismatched config and weights

#89 Unable to run SAM_Audio

#99 32gb ram/24gb vram oom

#98 Input to difussion through forward_args does not include span prediction even with predict_spans=True

#96 Text Prompting

#93 Windows: torchcodec conflicts with PyTorch 2.5+ (flex_attention missing vs DLL load failure)

#91 Playground doesn't work

#70 5090 Windows Install Notes - SAM Audio

#94 Inconsistent instrument separation in long tracks with local inference

#79 not working install via pip in google colab

#8 Add support for onnx inference

#95 01

#92 Mismatch between model configs and pe-audio-frame pre-trained models

#72 Audio Segmentation in Multi-Person Scenarios

#67 SAMAudioJudgeModel fails to import - requires perception_models which has numpy conflict

#88 感觉只能用cpu启启来

#90 Which huggingface_hub version you are using?

#85 Conflict dependences.

#47 [Guide] Windows Installation - Solving Dependency Hell (PyTorch Nightly + xformers/torchcodec workaround)