Instructions to use stabilityai/stable-audio-3-optimized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Stable Audio 3
How to use stabilityai/stable-audio-3-optimized with Stable Audio 3:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Fix missing 2π factor in seconds_freqs across all dit.onnx (FP32 source ONNX)
Browse filesThe base FP32 dit.onnx files were exported by an older version of the
producer (fast_load/build_dit.py) before the 2π fix was applied. The
post-surgery dit_fp16mixed.onnx files DID get the fix re-injected (their
seconds_freqs has max ≈ 62832 = 2π × 10000), but the source dit.onnx
files were never re-uploaded and still have max=10000.
Effect: any consumer building from dit.onnx (e.g., `--precision fp32`
path that reads sa3-m/dit.onnx, or anyone re-running build_dit_fp16mixed
locally) would inherit the silence-after-~5s bug — the seconds_total
conditioner produces frequencies 2π× too low, so the Fourier features
collapse and the model can't condition on duration beyond ~5s.
Surgical fix: read the (128,) seconds_freqs initializer in each dit.onnx,
multiply by 2π, write back. For sa3-m the buffer is in the .data sidecar
at offset 3072+512 bytes — read it from there, multiply, and inline the
result into the .onnx so the 5.8 GB .data file doesn't need to be
re-uploaded. For sa3-sm-music/sfx the buffer was already inline.
Reference build_dit.py:172 — `freqs = freqs * (2.0 * math.pi)`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- onnx/sa3-m/dit.onnx +2 -2
- onnx/sa3-sm-music/dit.onnx +2 -2
- onnx/sa3-sm-sfx/dit.onnx +2 -2
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:369ed7fa4cc0495f221df3c2a030071e82591289a3b249955537cb36a0af172b
|
| 3 |
+
size 3878882
|
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:196e4af5f577b207bda4ca6449fd43e1bb9d33f0813372d0d8e6a77181c2fc53
|
| 3 |
+
size 1839539412
|
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4d4ef70791db2530d7cf61e083c2353b0cffb3137517285f9dfa22969ccfc23
|
| 3 |
+
size 1839539412
|