You can deploy this model and start earning money today!

vokra/
canary-1b-flash

Name: canary-1b-flash
Availability: InStock

vokra

gguf

cc-by-4.0

Views

No views yet

canary-1b-flash (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-1b-flash.gguf`	3094.0 MB	`6b4212f5d8f2783061b8d61fc3d5d10b6e8e96d72f4d4bcb241fa603b381376f`

Usage

bash

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

vokra-cli run --model canary-1b-flash.gguf --input input.wav

Provenance

Field	Value
Architecture	`canary-1b-flash`
Tensors	1260
Upstream source	nvidia/canary-1b-flash (FastConformer encoder + Transformer AED decoder, flash-tuned 4-layer decoder for 1000+ RTFx, cc-by-4.0 attribution required)
Upstream licence	`cc-by-4.0`
Licence class	`attribution-required`
Registry model id	`canary-1b-flash`
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-Flash (multilingual multi-task ASR / AST — English / German / French / Spanish; FastConformer encoder + Transformer AED decoder — the flash-tuned variant of Canary-1B-v2 with a shrunk 4-layer decoder for 1000+ RTFx inference). Model weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) NVIDIA. Source: https://huggingface.co/nvidia/canary-1b-flash

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 canary-1b-flash.gguf
# expect: 6b4212f5d8f2783061b8d61fc3d5d10b6e8e96d72f4d4bcb241fa603b381376f