Skip to content
ModelListedExternal
Download

Htdemucs Models

4/6-Stem Source Separation — Vocals, Drums, Bass, Other (+Guitar, Piano)

Sourcehuggingface.co/AEmotionStudio/htdemucs-models/tree/1350068b40439d494f5a99e614230e15528a2403
KindOtherVersionRevision 1350068Cgrade

Model source

Kind
Other
File size
52.3–80.1 MB
Version
vRevision 1350068
Updated
Oct 10, 2026
Downloads
0
Source
Hugging Face

Source description

HTDemucs Models (Safetensors)

4/6-Stem Source Separation — Vocals, Drums, Bass, Other (+Guitar, Piano)

Original Source by Facebook Research · MIT License

Converted from the original .th checkpoint format to safetensors for faster loading and safer deserialization. For use with Mæstræa AI Workstation.

Available Models

FileStemsSizeDescription
htdemucs.safetensors4 (drums, bass, other, vocals)84 MBBase model
htdemucs_ft.safetensors4 (drums, bass, other, vocals)84 MBFine-tuned — best quality ⭐
htdemucs_6s.safetensors6 (drums, bass, other, vocals, guitar, piano)55 MB6-stem variant

Each model has a matching *_config.json with architecture parameters (sources, sample rate, channels).

What HTDemucs Does

HTDemucs (Hybrid Transformer Demucs) separates mixed audio into individual stems:

  • Vocals — Singing, spoken word
  • Drums — Percussion, kick, snare, hi-hat
  • Bass — Bass guitar, synth bass
  • Other — Everything else (keys, synths, FX)
  • Guitar — (6-stem model only)
  • Piano — (6-stem model only)

Key Features

  • Real-time capable on GPU
  • Adjustable segment size for VRAM control
  • Best-in-class separation quality (htdemucs_ft)
  • ~4–6 GB VRAM

Original Checkpoint URLs

These safetensors were converted from:

ModelOriginal URL
htdemucshttps://dl.fbaipublicfiles.com/demucs/hybrid_transformer/955717e8-8726e21a.th
htdemucs_fthttps://dl.fbaipublicfiles.com/demucs/hybrid_transformer/04573f0d-f3cf25b2.th
htdemucs_6shttps://dl.fbaipublicfiles.com/demucs/hybrid_transformer/5c90dfd2-34c22ccb.th

Usage with Mæstræa

These models are automatically downloaded by the Mæstræa AI Workstation backend. They can also be used directly with the demucs library:

from demucs.pretrained import get_model
model = get_model("htdemucs_ft")

License

MIT — same as the original Demucs release.

Credits

Sources

1 source
Hugging FacePrimaryVersion 1350068b40439d494f5a99e614230e15528a2403
huggingface.co/AEmotionStudio/htdemucs-models/tree/1350068b40439d494f5a99e614230e15528a2403

Verified Aug 14

Model artifacts

3 artifacts

htdemucs_6s.safetensors

safetensors · 52.3 MB · SHA-256 24b06179c643…9ea2 · Hugging Face

Download

htdemucs_ft.safetensors

safetensors · 80.1 MB · SHA-256 a89307833d7c…4d30 · Hugging Face

Download

htdemucs.safetensors

safetensors · 80.1 MB · SHA-256 36dc503a9ca7…7f17 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeAug 14huggingface.co/AEmotionStudio/htdemucs-models

--- license: mit tags: - audio - audio-separation - stem-separation - demucs - htdemucs - safetensors - maestraea pipeline_tag: audio-to-audio --- # HTDemucs Models (Safetensors) **4/6-Stem Source Separation — Vocals, Drums, Bass, Other (+Guitar, Piano)** [Original Source](https://github.com/facebookresearch/demucs) by [Facebook Research](https://github.com/facebookresearch) · MIT License > Converted from the original `.th` checkpoint format to safetensors for faster loading and safer deserialization. For use with [Mæstræa AI Workstation](https://github.com/AEmotionStudio/Maestraea). ## Available Models | File | Stems | Size | Description | |------|-------|------|-------------| | `htdemucs.safetensors` | 4 (drums, bass, other, vocals) | 84 MB | Base model | | `htdemucs_ft.safetensors` | 4 (drums, bass, other, vocals) | 84 MB | **Fine-tuned** — best quality ⭐ | | `htdemucs_6s.safetensors` | 6 (drums, bass, other, vocals, guitar, piano) | 55 MB | 6-stem variant | Each model has a matching `*_config.json` with architecture parameters (sources, sample rate, channels). ## What HTDemucs Does HTDemucs (Hybrid Transformer Demucs) separates mixed audio into individual stems: - **Vocals** — Singing, spoken word - **Drums** — Percussion, kick, snare, hi-hat - **Bass** — Bass guitar, synth bass - **Other** — Everything else (keys, synths, FX) - **Guitar** — (6-stem model only) - **Piano** — (6-stem model only) ### Key Features - Real-time capable on GPU - Adjustable segment size for VRAM control - Best-in-class separation quality (htdemucs_ft) - ~4–6 GB VRAM ## Original Checkpoint URLs These safetensors were converted from: | Model | Original URL | |-------|-------------| | htdemucs | `https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/955717e8-8726e21a.th` | | htdemucs_ft | `https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/04573f0d-f3cf25b2.th` | | htdemucs_6s | `https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/5c90dfd2-34c22ccb.th` | ## Usage with Mæstræa These models are automatically downloaded by the Mæstræa AI Workstation backend. They can also be used directly with the `demucs` library: ```python from demucs.pretrained import get_model model = get_model("htdemucs_ft") ``` ## License MIT — same as the original Demucs release. ## Credits - **Model**: [Facebook Research / Meta AI](https://github.com/facebookresea...

NoteAug 14huggingface.co/AEmotionStudio/htdemucs-models

Source context: 0 downloads · 0 likes · Pipeline audio-to-audio · Repo AEmotionStudio/htdemucs-models