GGUF
vokra
wespeaker / SOURCE.md
ayousanz's picture
Upload folder using huggingface_hub
a20ec15 verified
|
Raw
History Blame Contribute Delete
786 Bytes

Provenance — vokra/wespeaker

Field Value
Upstream source Wespeaker/wespeaker-voxceleb-resnet34-LM (ResNet34 speaker encoder, VoxCeleb + Large-Margin, apache-2.0)
Upstream licence apache-2.0
Architecture wespeaker
Tensors 219
SHA-256 d2dd9114179e28d14bd7c6ec372807823f1064c4f6cdc2349a83aa652635553d
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

vokra-cli convert --model <kind> --input <upstream> --output model.gguf
shasum -a 256 model.gguf   # expect d2dd9114179e28d14bd7c6ec372807823f1064c4f6cdc2349a83aa652635553d