sam-audio-shared / README.md
super135799's picture
AudioGhost copy of Meta's SAM-Audio weights: license, card, config, fp16 model and codec
5d42138 verified
|
Raw History Blame Contribute Delete
1.29 kB
---
license: other
license_name: sam-license
license_link: LICENSE
pipeline_tag: audio-to-audio
tags:
- audio
- source-separation
- sam-audio
- audioghost
---
# SAM-Audio shared components (AudioGhost copy)
Parts of Meta's [SAM-Audio](https://github.com/facebookresearch/sam-audio) that every model size shares, repackaged for
[AudioGhost](https://github.com/0x0funky/audioghost-ai). **Not made, endorsed or supported by Meta.**
- `audio_codec.safetensors`: the DACVAE audio codec in float32. It is identical in Meta's Small, Base and Large
checkpoints, so it is stored once here; the size repos (audioghostai/sam-audio-small, -base, -large) hold the transformers.
Source: `facebook/sam-audio-small@20b65f56888142eebe7c37448c6f6b3b32600e9b`.
## License
These weights are SAM Materials under Meta's **SAM License**, included here as [LICENSE](LICENSE). By downloading or
using them you agree to its terms, including the Trade Controls section. If you redistribute them, or anything derived
from them, you must do so under the same license and include a copy of it.
## Files
| File | Size | SHA-256 |
|---|---|---|
| `audio_codec.safetensors` | 430,723,572 bytes (410.8 MB) | `93929d357aadba28365a643cf5513dbb49e059a3045d7e8c0729108efd964a49` |