Instructions to use starkdmi/Demucs_MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use starkdmi/Demucs_MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Demucs_MLX starkdmi/Demucs_MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Demucs v4 / HTDemucs-ft (MLX)
Music source separation into drums, bass, other and vocals. Converted to MLX from the maintained Demucs v4 source and the official HTDemucs-ft weights.
Files
Four checkpoints, one per stem, 84 MB each:
| file | official upstream checkpoint |
|---|---|
drums.safetensors |
f7e0c4bc |
bass.safetensors |
d12395a8 |
other.safetensors |
92cfc3b6 |
vocals.safetensors |
04573f0d |
Each .json beside a checkpoint is that stem's architecture configuration.
HTDemucs-ft ships a separately fine-tuned checkpoint per stem, and each one emits all four sources โ the stem it is named for is the one it was tuned to produce best. Extracting a single stem therefore means downloading one 84 MB file, and a full four-stem separation runs the network four times.
fp32 only; no quantized conversion is published.
Licence
MIT, covering both the upstream code and the official HTDemucs-ft weights.
Used by
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for starkdmi/Demucs_MLX
Base model
adefossez/HTDemucs-ft