Cocktail Fork MRX Adapted Loudness

--- license: mit library_name: mlx tags: - mlx - audio - audio-source-separation - speech - music - apple-silicon pipeline_tag: audio-to-audio --- # Cocktail-Fork-MRX — `adapted-loudness` variant (MLX) Apple **MLX** port of MERL's **MRX** (Multi-Resolution CrossNet) — separates a soundtrack mixture into **music**, **speech**, and **sound effects (sfx)**. **This variant** uses the `adapted_loudness_` checkpoint: adapted with **loudness normalization** for better alignment with real cinematic/movie stems. Try this (and `-adapted-eq`) on real soundtrack content. Other variants: [`Cocktail-Fork-MRX`](https://huggingface.co/mlx-community/Cocktail-Fork-MRX) (default) · [`-paper`](https://huggingface.co/mlx-community/Cocktail-Fork-MRX-paper) (ICASSP reproduction) · [`-adapted-eq`](https://huggingface.co/mlx-community/Cocktail-Fork-MRX-adapted-eq). - **Upstream:** [merlresearch/cocktail-fork-separation](https://github.com/merlresearch/cocktail-fork-separation) (MIT) · *The Cocktail Fork Problem*, ICASSP 2022. - **Parity:** numerically exact vs PyTorch (full-forward max_abs ≈ `6e-7`). ## Usage ```bash pip install git+https://github.com/xocialize/cocktail-fork-mlx cocktail-fork-mlx --audio-path soundtrack.wav --out-dir ./out \ --weights mlx-community/Cocktail-Fork-MRX-adapted-loudness ``` ~30.6M params, fp32 (122 MB), 44.1 kHz. MIT, © MERL for the original model/weights.

Source context: 23 downloads · 1 likes · Pipeline audio-to-audio · Library mlx · Repo mlx-community/Cocktail-Fork-MRX-adapted-loudness

Source context: 10 downloads · 1 likes · Pipeline audio-to-audio · Library mlx · Repo mlx-community/Cocktail-Fork-MRX-adapted-loudness