ast-finetuned-audioset (Vokra GGUF)

Converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.

This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.

Files

File	Size	SHA-256
ast.gguf	330.4 MB	f06bf05078d4267193554ec76e143f8541bd3130c3a81ae2a3d6b5424c8b1ac2

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o ast.gguf \
  https://huggingface.co/vokra/ast-finetuned-audioset/resolve/main/ast.gguf

vokra-cli run --model ast.gguf --input input.wav

Provenance

Field	Value
Architecture	ast
Tensors	203
Upstream source	MIT/ast-finetuned-audioset-10-10-0.4593 (Audio Spectrogram Transformer, ViT over spectrogram, 527-class AudioSet fine-tune, bsd-3-clause)
Upstream licence	bsd-3-clause
Licence class	permissive
Registry model id	ast-finetuned-audioset
Vokra GGUF schema	1
Converted by	vokra-core 0.1.0-alpha.0

Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.

Licence

The weights are distributed under bsd-3-clause, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 ast.gguf
# expect: f06bf05078d4267193554ec76e143f8541bd3130c3a81ae2a3d6b5424c8b1ac2