You can deploy this model and start earning money today!

vokra/
wav2vec2-large-xlsr-53-arabic

Name: wav2vec2-large-xlsr-53-arabic
Availability: InStock

vokra

gguf

apache-2.0

Views

No views yet

wav2vec2-large-xlsr-53-arabic (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
`xlsr-53-arabic.restamped.gguf`	1203.5 MB	`abd8fa08e70f6a7d0b5167b0cbae8d0eec9d070039e93d4273926a2ac63ad8df`

Usage

bash

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o xlsr-53-arabic.restamped.gguf \
  https://huggingface.co/vokra/wav2vec2-large-xlsr-53-arabic/resolve/main/xlsr-53-arabic.restamped.gguf

vokra-cli run --model xlsr-53-arabic.restamped.gguf --input input.wav

Provenance

Field	Value
Architecture	`wav2vec2_ctc`
Tensors	424
Upstream source	jonatasgrosman/wav2vec2-large-xlsr-53-arabic
Upstream licence	`apache-2.0`
Licence class	`permissive`
Registry model id	`wav2vec2-large-xlsr-53-arabic`
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.

Attribution required

jonatasgrosman (Wav2Vec2 XLSR-53 Arabic CTC fine-tune)

This licence obliges you to display the attribution above when you ship something built on these weights. Vokra surfaces it at runtime via vokra_model_attribution (C ABI) and a CLI banner.

Verifying this file

bash

shasum -a 256 xlsr-53-arabic.restamped.gguf
# expect: abd8fa08e70f6a7d0b5167b0cbae8d0eec9d070039e93d4273926a2ac63ad8df