# Provenance — vokra/sepformer-libri3mix

| Field | Value |
|---|---|
| Upstream source | speechbrain/sepformer-libri3mix (SepFormer 3-speaker cocktail-party separation, LibriMix corpus CC-BY-4.0, apache-2.0) |
| Upstream licence | `apache-2.0` |
| Architecture | `sepformer` |
| Tensors | 417 |
| SHA-256 | `5c560c27217e1037bbd150edbe29056d1c2fa7eaaaaeaa81fc59701d030bc2ca` |
| Converted by | vokra-core 0.1.0-alpha.0 |
| GGUF schema generation | 1 |

Every row is read from the artifact's own `vokra.*` metadata; none of it
is supplied by hand, so this file cannot disagree with the weight it
describes.

## Reproducing

```bash
vokra-cli convert --model <kind> --input <upstream> --output sepformer-libri3mix.gguf
shasum -a 256 sepformer-libri3mix.gguf   # expect 5c560c27217e1037bbd150edbe29056d1c2fa7eaaaaeaa81fc59701d030bc2ca
```