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] hf download starkdmi/Demucs_MLX --local-dir Demucs_MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Neutral wording, single-machine caveat, correct project link
Browse files
README.md
CHANGED
|
@@ -27,20 +27,17 @@ Four checkpoints, one per stem, 84 MB each:
|
|
| 27 |
|
| 28 |
Each `.json` beside a checkpoint is that stem's architecture configuration.
|
| 29 |
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
combined one, and a full four-stem separation runs the network four times.
|
| 35 |
|
| 36 |
fp32 only; no quantized conversion is published.
|
| 37 |
|
| 38 |
-
## Use
|
| 39 |
-
|
| 40 |
-
Consumed by [AudioToolSwift](https://github.com/starkdmi) as
|
| 41 |
-
`ModelRepository.demucs`, which pins this repository to an exact revision and
|
| 42 |
-
verifies the SHA-256 of every file it downloads.
|
| 43 |
-
|
| 44 |
## Licence
|
| 45 |
|
| 46 |
MIT, covering both the upstream code and the official HTDemucs-ft weights.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
Each `.json` beside a checkpoint is that stem's architecture configuration.
|
| 29 |
|
| 30 |
+
HTDemucs-ft ships a separately fine-tuned checkpoint per stem, and each one emits
|
| 31 |
+
all four sources — the stem it is named for is the one it was tuned to produce
|
| 32 |
+
best. Extracting a single stem therefore means downloading one 84 MB file, and a
|
| 33 |
+
full four-stem separation runs the network four times.
|
|
|
|
| 34 |
|
| 35 |
fp32 only; no quantized conversion is published.
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
## Licence
|
| 38 |
|
| 39 |
MIT, covering both the upstream code and the official HTDemucs-ft weights.
|
| 40 |
+
|
| 41 |
+
## Used by
|
| 42 |
+
|
| 43 |
+
[AudioToolSwift](https://github.com/starkdmi/AudioToolSwift)
|