Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Stable Audio Morph Onnx

stability-ai-community

Quellehuggingface.co/shoegazerstella/stable-audio-morph-onnx/tree/97c6c9d59a2a83d3644e91da2711a5351c3da648
ArtOtherBasismodellstabilityai/stable-audio-3-small-musicVersionDecoder fp16CBewertung

Modellquelle

Art
Other
Dateigröße
104–105 MB
Basismodell
stabilityai/stable-audio-3-small-music
Version
vDecoder fp16
Aktualisiert
22. Okt. 2026
Quelle
Hugging Face

Quellenbeschreibung

Stable Audio Morph — ONNX Models

ONNX FP16 exports of the SAME autoencoder from Stable Audio 3 Small-Music for browser-based latent space audio morphing.

Models

FileSizeDescription
encoder_fp16.onnx104 MBEncodes 10s stereo audio (44.1kHz) to latent [1, 256, 108]
decoder_fp16.onnx105 MBDecodes latent [1, 256, 108] to stereo audio

Usage

These models run in the browser via ONNX Runtime Web with WebGPU or WASM backends.

import * as ort from "onnxruntime-web";

const encoder = await ort.InferenceSession.create("encoder_fp16.onnx");
const decoder = await ort.InferenceSession.create("decoder_fp16.onnx");

// Encode audio to latent
const input = new ort.Tensor("float32", audioData, [1, 2, 441000]);
const { latent } = await encoder.run({ audio: input });

// Decode latent to audio
const { audio } = await decoder.run({ latent });

Source

  • Original model: stabilityai/stable-audio-3-small-music
  • Original repo: Stability-AI/stable-audio-3
  • Paper: Stable Audio 3 (Stability AI, 2025)
  • Autoencoder: SAME (Semantic-Acoustic autoencoder), 108M parameters
  • Compression ratio: 4096x (44.1kHz stereo to 256-dim latent at ~10.8 Hz)
  • Training data: AudioSparx (806K recordings) + Freesound (472K recordings)

Export Details

  • Exported from SA3 Small-Music checkpoint using torch.onnx.export (opset 18)
  • Converted to FP16 via onnxconverter-common
  • Validated: round-trip correlation > 0.99
  • No text encoder included (T5Gemma removed for latent-only usage)

Technical Specs

  • Input (encoder): [1, 2, 441000] float32 — 10 seconds stereo at 44.1kHz
  • Output (encoder): [1, 256, 108] float32 — 256-dim latent, 108 temporal frames
  • Input (decoder): [1, 256, 108] float32
  • Output (decoder): [1, 2, 442368] float32 — stereo audio

License

These weights are derived from Stability AI's Stable Audio 3 model. Usage is subject to the Stability AI Community License.

Quellen

1 Quelle
Hugging FacePrimärVersion 97c6c9d59a2a83d3644e91da2711a5351c3da648
huggingface.co/shoegazerstella/stable-audio-morph-onnx/tree/97c6c9d59a2a83d3644e91da2711a5351c3da648

Verifiziert 7. Aug.

Modellartefakte

2 Artefakte

decoder_fp16.onnx

onnx · 105 MB · SHA-256 a58743af5959…3ac2 · Hugging Face

Herunterladen

encoder_fp16.onnx

onnx · 104 MB · SHA-256 ec52ea795494…7909 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge
Readme7. Aug.huggingface.co/shoegazerstella/stable-audio-morph-onnx

--- license: other license_name: stability-ai-community license_link: https://huggingface.co/stabilityai/stable-audio-3-small-music/blob/main/LICENSE.md tags: - audio - music - onnx - webgpu - stable-audio - autoencoder pipeline_tag: audio-to-audio base_model: stabilityai/stable-audio-3-small-music --- # Stable Audio Morph — ONNX Models ONNX FP16 exports of the **SAME autoencoder** from [Stable Audio 3 Small-Music](https://huggingface.co/stabilityai/stable-audio-3-small-music) for browser-based latent space audio morphing. ## Models | File | Size | Description | |------|------|-------------| | `encoder_fp16.onnx` | 104 MB | Encodes 10s stereo audio (44.1kHz) to latent [1, 256, 108] | | `decoder_fp16.onnx` | 105 MB | Decodes latent [1, 256, 108] to stereo audio | ## Usage These models run in the browser via [ONNX Runtime Web](https://onnxruntime.ai/docs/get-started/with-javascript/web.html) with WebGPU or WASM backends. ```javascript import * as ort from "onnxruntime-web"; const encoder = await ort.InferenceSession.create("encoder_fp16.onnx"); const decoder = await ort.InferenceSession.create("decoder_fp16.onnx"); // Encode audio to latent const input = new ort.Tensor("float32", audioData, [1, 2, 441000]); const { latent } = await encoder.run({ audio: input }); // Decode latent to audio const { audio } = await decoder.run({ latent }); ``` ## Source - **Original model**: [stabilityai/stable-audio-3-small-music](https://huggingface.co/stabilityai/stable-audio-3-small-music) - **Original repo**: [Stability-AI/stable-audio-3](https://github.com/Stability-AI/stable-audio-3) - **Paper**: Stable Audio 3 (Stability AI, 2025) - **Autoencoder**: SAME (Semantic-Acoustic autoencoder), 108M parameters - **Compression ratio**: 4096x (44.1kHz stereo to 256-dim latent at ~10.8 Hz) - **Training data**: AudioSparx (806K recordings) + Freesound (472K recordings) ## Export Details - Exported from SA3 Small-Music checkpoint using `torch.onnx.export` (opset 18) - Converted to FP16 via `onnxconverter-common` - Validated: round-trip correlation > 0.99 - No text encoder included (T5Gemma removed for latent-only usage) ## Technical Specs - **Input (encoder)**: `[1, 2, 441000]` float32 — 10 seconds stereo at 44.1kHz - **Output (encoder)**: `[1, 256, 108]` float32 — 256-dim latent, 108 temporal frames - **Input (decoder)**: `[1, 256, 108]` float32 - **Output (de...

Note7. Aug.huggingface.co/shoegazerstella/stable-audio-morph-onnx

Source context: 0 downloads · 1 likes · Pipeline audio-to-audio · Repo shoegazerstella/stable-audio-morph-onnx