Skip to content
ModelListedExternal
Browse files

Htdemucs Ft Onnx

An ONNX export of the Hybrid Transformer Demucs fine-tuned 4-stem model (htdemucsft), used by Silverdaw as its backup stem-separation engine. htdemucsft is a "bag" of four specialist models — one per source — so...

KindOtherVersionHtdemucs ft bassCgrade

Model source

Kind
Other
File size
302 MB
Version
vHtdemucs ft bass
Updated
Oct 11, 2026
Source
Hugging Face

Source description

Silverdaw Backup Stem Pack — htdemucs fine-tuned (ONNX)

An ONNX export of the Hybrid Transformer Demucs fine-tuned 4-stem model (htdemucs_ft), used by Silverdaw as its backup stem-separation engine. htdemucs_ft is a "bag" of four specialist models — one per source — so vocals / drums / bass / other are all native outputs.

Silverdaw's primary engine is the higher-quality RoFormer pack pair (vocals + rhythm); this model is used when those packs are not installed, or when the user explicitly selects the backup engine.

This repository is a re-host of StemSplitio/htdemucs-ft-onnx so Silverdaw can serve every model it needs from one self-owned location. The weights and the export are unchanged (byte-identical; same SHA-256).

Files

FileSizeStemSHA-256
htdemucs_ft_vocals.onnx~302 MBvocals8c5d5e2da1f27050240bb80236673307ee3b40d4b064066d9350f4d64bfd544d
htdemucs_ft_drums.onnx~302 MBdrumsf76b68af36066e38885b369299b5032a861038f9b49da5aa6cf1c31cfa69cf27
htdemucs_ft_bass.onnx~302 MBbass2a74d9283fc2336fcc58d50f87a7080aff57aea372f65cfe3f0211ea1ff16182
htdemucs_ft_other.onnx~302 MBother90e11806c1bb558ca9d9c7e909d28a2854f7f217982e90482dbed6442513daad

Each file is a self-contained .onnx (fp32 weights, no external .data). fp32 is chosen over the fp16 variants for the CPU execution provider, where fp16 ops are commonly emulated (slower) rather than accelerated.

Provenance & license

License: MIT.

  • Weights — © Meta / Alexandre Défossez et al., Demucs v4 (Hybrid Transformer Demucs, fine-tuned), released under MIT.
  • ONNX export — © StemSplitio (StemSplitio/htdemucs-ft-onnx).
  • Architecture / paper — Hybrid Transformers for Music Source Separation (Rouard, Massa, Défossez; arXiv:2211.08553) / facebookresearch/demucs (MIT).

Intended use

Designed for offline (non-real-time) stem separation inside a desktop DAW. It is not a real-time audio-callback model — run it on a worker/background thread.

Sources

1 source
Hugging FacePrimaryVersion 7209a8562fd008ca38264500b168095679f85ad7
huggingface.co/silverdaw/htdemucs-ft-onnx/tree/7209a8562fd008ca38264500b168095679f85ad7

Verified Oct 11

Download files

Model artifacts

4 artifacts

htdemucs_ft_bass.onnx

onnx · 302 MB · SHA-256 2a74d9283fc2…6182 · Hugging Face

Download file

htdemucs_ft_drums.onnx

onnx · 302 MB · SHA-256 f76b68af3606…cf27 · Hugging Face

Download file

htdemucs_ft_other.onnx

onnx · 302 MB · SHA-256 90e11806c1bb…daad · Hugging Face

Download file

htdemucs_ft_vocals.onnx

onnx · 302 MB · SHA-256 8c5d5e2da1f2…544d · Hugging Face

Download file

Source excerpts

2 excerpts

--- license: mit library_name: onnxruntime pipeline_tag: audio-to-audio tags: - onnx - onnxruntime - audio - music - source-separation - stem-separation - demucs - htdemucs - hybrid-transformer-demucs - vocals - drums - bass --- # Silverdaw Backup Stem Pack — htdemucs fine-tuned (ONNX) An ONNX export of the **Hybrid Transformer Demucs** fine-tuned 4-stem model (`htdemucs_ft`), used by [Silverdaw](https://github.com/irarainey/silverdaw) as its **backup** stem-separation engine. `htdemucs_ft` is a "bag" of four specialist models — one per source — so vocals / drums / bass / other are all native outputs. Silverdaw's primary engine is the higher-quality RoFormer pack pair ([vocals](https://huggingface.co/silverdaw/mel-band-roformer-vocals-onnx) + [rhythm](https://huggingface.co/silverdaw/bs-roformer-rhythm-onnx)); this model is used when those packs are not installed, or when the user explicitly selects the backup engine. This repository is a **re-host** of [`StemSplitio/htdemucs-ft-onnx`](https://huggingface.co/StemSplitio/htdemucs-ft-onnx) so Silverdaw can serve every model it needs from one self-owned location. The weights and the export are unchanged (byte-identical; same SHA-256). ## Files | File | Size | Stem | SHA-256 | | --- | --- | --- | --- | | `htdemucs_ft_vocals.onnx` | ~302 MB | vocals | `8c5d5e2da1f27050240bb80236673307ee3b40d4b064066d9350f4d64bfd544d` | | `htdemucs_ft_drums.onnx` | ~302 MB | drums | `f76b68af36066e38885b369299b5032a861038f9b49da5aa6cf1c31cfa69cf27` | | `htdemucs_ft_bass.onnx` | ~302 MB | bass | `2a74d9283fc2336fcc58d50f87a7080aff57aea372f65cfe3f0211ea1ff16182` | | `htdemucs_ft_other.onnx` | ~302 MB | other | `90e11806c1bb558ca9d9c7e909d28a2854f7f217982e90482dbed6442513daad` | Each file is a self-contained `.onnx` (fp32 weights, no external `.data`). fp32 is chosen over the fp16 variants for the CPU execution provider, where fp16 ops are commonly emulated (slower) rather than accelerated. ## Provenance & license **License: MIT.** - **Weights** — © Meta / Alexandre Défossez et al., *Demucs v4* (Hybrid Transformer Demucs, fine-tuned), released under MIT. - **ONNX export** — © StemSplitio ([`StemSplitio/htdemucs-ft-onnx`](https://huggingface.co/StemSplitio/htdemucs-ft-onnx)). - **Architecture / paper** — *Hybrid Transformers for Music Source Separation* (Rouard, Massa...

Source context: 0 downloads · 0 likes · Pipeline audio-to-audio · Library onnxruntime · Repo silverdaw/htdemucs-ft-onnx