GGUF
vokra
xvector / SOURCE.md
ayousanz's picture
Upload folder using huggingface_hub
9b0530f verified
|
Raw
History Blame Contribute Delete
758 Bytes
# Provenance — vokra/xvector
| Field | Value |
|---|---|
| Upstream source | speechbrain/spkrec-xvect-voxceleb (TDNN X-vector speaker encoder, apache-2.0) |
| Upstream licence | `apache-2.0` |
| Architecture | `xvector` |
| Tensors | 46 |
| SHA-256 | `a1aaad3efe781a45683cdec08bc0b4d5c7618f613ed3241be0d7230e6b28981a` |
| 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 xvector.gguf
shasum -a 256 xvector.gguf # expect a1aaad3efe781a45683cdec08bc0b4d5c7618f613ed3241be0d7230e6b28981a
```