sber-gigaam-multilingual (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
sber-gigaam-multilingual.gguf	842.1 MB	74fd0d6dd84de2ce2ecaf0f8b8f13572bb3a81c44241f59814beb85389186b5a

Usage

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

vokra-cli run --model sber-gigaam-multilingual.gguf --input input.wav

Provenance

Field	Value
Architecture	gigaam_multilingual
Tensors	552
Upstream source	salute-developers/GigaAM (multilingual variant, char-wise CTC, 70+ languages, MIT)
Upstream licence	mit
Licence class	permissive
Registry model id	sber-gigaam-multilingual
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 mit, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 sber-gigaam-multilingual.gguf
# expect: 74fd0d6dd84de2ce2ecaf0f8b8f13572bb3a81c44241f59814beb85389186b5a