A domain-specialized fine-tune of Meta AI's htdemucs_6s trained exclusively to extract clean, isolated guitar stems from dense, real-world studio mixes.
TL;DR: Drop in any song. Get back a clean guitar stem. Works on clean riffs, distorted rock, acoustic, and layered studio productions.
Results
Evaluated on a 24-track held-out split of MoisesDB v0.1 using full-track BSS metrics (deterministic shifts=0):
Model
SDR ↑ (dB)
SIR ↑ (dB)
SAR ↑ (dB)
Stock htdemucs_6s (Meta AI baseline)
8.42
20.41
6.28
htdemucs-6s-guitar-ft (this model)
8.73
21.30
6.65
Δ improvement
+0.31
+0.89
+0.37
The +0.89 dB SIR gain is the headline result — it directly measures guitar clarity and bleed rejection. Less drum transient, less bass rumble, less cymbal wash bleeding into your extracted guitar stem.
Quick Start
python
1from demucs.pretrained import get_model
2from demucs.applyimport apply_model
3from huggingface_hub import hf_hub_download
4import torch
5import soundfile as sf
67GUITAR_STEM_INDEX =4# htdemucs_6s: [drums, bass, other, vocals, guitar, piano]89# Download fine-tuned weights from HuggingFace10checkpoint_path = hf_hub_download(11 repo_id="adityalakhani/htdemucs-6s-guitar-ft",12 filename="guitar_htdemucs_6s.pt"13)1415# Load base model architecture16model = get_model("htdemucs_6s")1718# Load and unwrap fine-tuned weights (training dict)19checkpoint = torch.load(checkpoint_path, map_location="cpu", weights_only=True)20state_dict = checkpoint["model_state_dict"]2122# Remap keys to match demucs' BagOfModels wrapper23state_dict ={f"models.0.{k}": v for k, v in state_dict.items()}24model.load_state_dict(state_dict)25model.eval()2627# Load audio (must be 44100 Hz. soundfile avoids torchaudio Windows DLL issues)28audio_np, sr = sf.read("your_song.wav", always_2d=True, dtype="float32")29waveform = torch.from_numpy(audio_np.T)# (C, T)30if waveform.shape[0]==1:31 waveform = waveform.repeat(2,1)3233# Separate using apply_model for proper overlap-add chunking34with torch.no_grad():35 stems = apply_model(model, waveform.unsqueeze(0), shifts=1, overlap=0.25)36 guitar = stems[0, GUITAR_STEM_INDEX]3738sf.write("guitar_stem.wav", guitar.T.numpy(), samplerate=44100, subtype="PCM_24")39print("Done.")
Or use the included CLI script for any audio file format (mp3, flac, wav, etc.):
This model is a fine-tuned checkpoint of htdemucs_6s — Meta AI's Hybrid Transformer Demucs (6-source variant). The architecture processes audio simultaneously in two domains:
Time domain: Raw waveform → 1D Conv encoder → Cross-Domain Transformer → 1D ConvTranspose decoder
Both decoder outputs are summed to produce each separated stem. The model outputs 6 stems: drums, bass, other, vocals, guitar (index 4), piano.
~80M total parameters.
What makes this different from stock htdemucs_6s?
The pre-trained htdemucs_6s is a general-purpose separator trained on MUSDB18-HQ — a broad mix of musical genres. This fine-tuned version was subsequently trained on MoisesDB (240 real multitrack songs with professionally isolated guitar stems), which produces a model that has developed a much stronger prior for real guitar acoustic and spectral characteristics.
The result is a model that:
Rejects drum transient bleed more aggressively (+0.89 dB SIR)
More precisely follows guitar sustain curves vs. background noise
Is better calibrated for the full guitar frequency range (clean highs to distorted lows)
Training Details
Dataset
MoisesDB v0.1 — 240 real commercial multitrack songs with professionally isolated stems:
Each song contains ground-truth isolated guitar WAV files
Covers Rock, Singer-Songwriter, Pop, Latin, and Electronic genres
Guitar stems are harmonically and rhythmically interlocked with their actual mix — no synthetic mix construction
Split: 216 songs training / 24 songs validation (stratified by genre via fixed-seed shuffle).
Fine-Tuning Strategy
Training was split into two phases to prevent catastrophic forgetting:
Phase
Layers Active
LR
Epochs
Phase 1 (Warmup)
Decoders only (Encoder + Transformer frozen)
3×10⁻⁴
20
Phase 2 (Fine-tune)
Full network unfrozen
1×10⁻⁴
~55 (early stopped)
The GradScaler was explicitly reset at the Phase 1 → Phase 2 transition to prevent the sudden encoder gradient regime from destabilizing the decoder weights learned in Phase 1.
Loss Function
L_total = L1(pred, target)
+ 0.5 × MultiResolutionSTFT(pred, target)
+ SI-SDR(pred, target) # weighted to zero on silent chunks (RMS < 1e-4)
L1 provides waveform fidelity
Multi-Resolution STFT adds spectral phase and magnitude matching across 3 FFT sizes
SI-SDR (Scale-Invariant SDR) directly optimizes the deployment metric — added in V4 to break through the +5.3 dB plateau
Data Augmentation
Remix augmentation (80%): For each training chunk, non-guitar stems (drums, bass, vocals, etc.) are independently swapped from random other songs in the dataset. This prevents the model from memorising song-specific mix signatures.
Guitar gain randomisation: Guitar stem scaled randomly in [-6 dB, +6 dB] before mixing.
Chunk length: 7.8 seconds (matches the model's effective receptive field).
Hyperparameters
Parameter
Value
Batch size
1
Gradient accumulation
4 steps (effective batch = 4)
Mixed precision
fp16 (torch.autocast + GradScaler)
Early stopping patience
10 epochs (on val loss)
Gradient clipping
max_norm = 1.0
Total training epochs
75 (early stopped)
Limitations
Heavy multi-guitar polyphony: When a mix contains 3+ overlapping guitars (lead + rhythm + acoustic), the model extracts all of them into a single stem — it does not separate individual guitar layers from each other. This is by design for the source separation stage of a larger pipeline.
Extreme distortion + cymbal bleed: Very high-gain metal tones (wall-of-sound production) with heavy cymbal wash remain the hardest cases. The model reduces bleed significantly but does not eliminate it.
Piano / keyboard ambiguity: Synth pads in the upper mid-frequency range can occasionally bleed into the guitar output on dense electronic productions. This is inherited from the base htdemucs_6s architecture.
Mono input: Mono audio is automatically upmixed to stereo before inference; results may be slightly less precise than native stereo input.
How to Cite
If you use this model in research or a project, please cite:
bibtex
1@misc{lakhani2026htdemucs_guitar_ft,
2 title = {Guitar Domain Expert HTDemucs 6s: A Domain-Specialized Fine-Tune of HTDemucs for Guitar Stem Extraction},
3 author = {Lakhani, Aditya},
4 year = {2026},
5 url = {https://huggingface.co/adityalakhani/htdemucs-6s-guitar-ft},
6}
Acknowledgements
Meta AI Research — HTDemucs architecture and pre-trained weights (demucs==4.0.1)
Moises.ai — MoisesDB v0.1 multitrack dataset used for domain fine-tuning
auraloss — Multi-Resolution STFT loss implementation (auraloss==0.4.0)
License
This model is released under the Apache 2.0 license. The base htdemucs_6s weights (Meta AI) are released under MIT. MoisesDB data is used in compliance with Moises.ai's research licensing terms; raw audio data is not redistributed.
