canary-1b-v2 (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
canary.gguf	2387.1 MB	26d401ec2d435376aa90a01a9856fa8ea8fd2e62c7b721fe338a77ac1a24111c

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o canary.gguf \
  https://huggingface.co/vokra/canary-1b-v2/resolve/main/canary.gguf

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

Provenance

Field	Value
Architecture	canary
Tensors	688
Upstream source	https://huggingface.co/nvidia/canary-1b-v2
Upstream licence	CC-BY-4.0
Licence class	attribution-required
Registry model id	nvidia/canary-1b-v2
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 CC-BY-4.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Attribution required

This application uses NVIDIA Canary-1B-v2 (multilingual multi-task ASR / AST — 25 European languages; FastConformer encoder + Transformer decoder AED). Model weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) NVIDIA. Source: https://huggingface.co/nvidia/canary-1b-v2

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

shasum -a 256 canary.gguf
# expect: 26d401ec2d435376aa90a01a9856fa8ea8fd2e62c7b721fe338a77ac1a24111c