File	Size	Purpose
`denoiser.safetensors`	41 MB	2D UNet spectral-mask denoiser
`lcfm_ae.safetensors`	390 MB	IRMAE encoder/decoder (mel <-> 64-dim latent)
`lcfm_cfm.safetensors`	264 MB	Conditional flow matching, 30-layer WaveNet velocity field
`vocoder.safetensors`	662 MB	UnivNet vocoder (LVCNet generator)
`normalizer.safetensors`	160 B	Mel running mean/variance

Total: ~1.4 GB at float32.

Usage

With resemble-enhance-swift:

huggingface-cli download sammcj/resemble-enhance-mlx

The CLI and example SwiftUI app auto-discover weights from the HuggingFace hub cache (~/.cache/huggingface/hub/models--sammcj--resemble-enhance-mlx/snapshots/<commit>/). You can also pass the directory explicitly:

resemble-enhance enhance \
  --model-dir ~/.cache/huggingface/hub/models--sammcj--resemble-enhance-mlx/snapshots/<commit>/ \
  input.wav output.wav

Or from Swift:

swift

import ResembleEnhance

let engine = try ResembleEnhance(modelDirectory: weightsURL)
let enhanced = engine.enhance(samples: samples, sampleRate: 24_000)

Conversion

Produced by Scripts/convert_weights.py in resemble-enhance-swift. The script:

Loads mp_rank_00_model_states.pt from the upstream PyTorch checkpoint (DeepSpeed format, wrapped in ["module"])
Fuses weight_norm parametrisations into plain weight tensors (handles both old weight_g/weight_v and new parametrizations.weight.original* formats)
Transposes conv kernels from PyTorch NCHW to MLX NHWC layout (Conv1d O,I,K -> O,K,I; Conv2d O,I,H,W -> O,H,W,I; ConvTranspose1d I,O,K -> O,K,I)
Transposes FIR filter buffers used by the alias-free resampler (same layout, since they're applied as conv kernels)
Splits the monolithic checkpoint into one safetensors file per component
Strips unused buffers (dummy, mel_fn, mrstft, training-only estimator)

To reproduce:

huggingface-cli download ResembleAI/resemble-enhance
python Scripts/convert_weights.py

The output then matches what's in this repo.

Source

Derived from ResembleAI/resemble-enhance. The original PyTorch checkpoint is mp_rank_00_model_states.pt from the enhancer_stage2 training run.

Licence and credit

Released under CC-BY-NC-4.0, inheriting the upstream licence. Non-commercial use only.

The model architecture, training data, training code, and original weights are the work of Resemble AI. This repo only contains the format conversion required to run the model on Apple Silicon via MLX. All credit for the model itself belongs to the original authors:

smcleod/resemble-enhance-mlx

resemble-enhance-mlx

Files

Usage

Conversion

Source

Licence and credit

smcleod/
resemble-enhance-mlx