wav2vec2-base-960h (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
wav2vec2-base-960h.gguf	360.1 MB	93e25755562bfb557f2a2b4d8844873451568617f54a83552793f953be0ff7ee

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o wav2vec2-base-960h.gguf \
  https://huggingface.co/vokra/wav2vec2-base-960h/resolve/main/wav2vec2-base-960h.gguf

vokra-cli run --model wav2vec2-base-960h.gguf --input input.wav

Provenance

Field	Value
Architecture	wav2vec2_ctc
Tensors	212
Upstream source	facebook/wav2vec2-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	wav2vec2-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

shasum -a 256 wav2vec2-base-960h.gguf
# expect: 93e25755562bfb557f2a2b4d8844873451568617f54a83552793f953be0ff7ee