Modelpublic

vokra/data2vec-audio-base

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes5downloads

Model Card

data2vec-audio-base (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
`model.gguf`	355.5 MB	`b9f73f8b825d2aabd5ddd82d13d07a67a0f6d13cf6284d1b3c52eb7ee9cb5dc0`

Usage

bash

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o model.gguf \
  https://huggingface.co/vokra/data2vec-audio-base/resolve/main/model.gguf

bash

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

Provenance

Field	Value
Architecture	`wav2vec2_ctc`
Tensors	232
Upstream source	facebook/data2vec-audio-base-960h (wav2vec 2.0 waveform-in encoder + optional CTC head, apache-2.0)
Upstream licence	`apache-2.0`
Licence class	`permissive`
Registry model id	`data2vec-audio-base-960h`
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 apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

bash

shasum -a 256 model.gguf
# expect: b9f73f8b825d2aabd5ddd82d13d07a67a0f6d13cf6284d1b3c52eb7ee9cb5dc0