| --- |
| license: apache-2.0 |
| base_model: OpenMOSS-Team/MOSS-SoundEffect |
| tags: |
| - mlx |
| - audio |
| - sound-effects |
| - text-to-audio |
| --- |
| |
| # MOSS-SoundEffect — MLX selective 4-bit (Swift-compatible) |
|
|
| Selective 4-bit (affine, group size 64) MLX conversion of |
| [`OpenMOSS-Team/MOSS-SoundEffect`](https://huggingface.co/OpenMOSS-Team/MOSS-SoundEffect), |
| a sound-effect / ambient generator on the MossTTSDelay architecture. |
|
|
| **Selective quant:** `lm_heads` and the input embeddings are kept **dense** |
| (full precision); only the transformer body is 4-bit. This matches the module |
| layout in [`mlx-audio-swift`](https://github.com/Blaizzy/mlx-audio-swift)'s |
| `MossTTSModel`, which defines those layers as plain (non-quantized) modules — a |
| fully-4-bit checkpoint fails to load there with a size mismatch. ~16 GB bf16 → |
| ~5.4 GB. |
|
|
| ## Usage (Swift) |
|
|
| Requires the patched fork [`nullic/mlx-audio-swift`](https://github.com/nullic/mlx-audio-swift) |
| (branch `trails`): adds float32 audio-token sampling + quantized-checkpoint |
| loading to `MossTTSModel`. Pair with the **original** audio tokenizer |
| [`OpenMOSS-Team/MOSS-Audio-Tokenizer`](https://huggingface.co/OpenMOSS-Team/MOSS-Audio-Tokenizer). |
|
|
| Sampling: audio temperature 1.7, top-p 0.8, top-k 25 (the upstream reference |
| settings; the fork's float32 sampling is what makes 1.7 coherent rather than noise). |
|
|
| ## License |
|
|
| Apache-2.0, inherited from the base model. Conversion only; no weights authored here. |
|
|
