---
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, Défossez; arXiv:2211.08553) /
  [`facebookresearch/demucs`](https://github.com/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.