parakeet-tdt-1.1b (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
parakeet-tdt-1.1b.gguf	4083.9 MB	5abd74cdffd5795b69b808f3c2164687cb906c181dfe19bf5e76bf3cad82126a

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o parakeet-tdt-1.1b.gguf \
  https://huggingface.co/vokra/parakeet-tdt-1.1b/resolve/main/parakeet-tdt-1.1b.gguf

vokra-cli run --model parakeet-tdt-1.1b.gguf --input input.wav

Provenance

Field	Value
Architecture	parakeet-tdt-1_1b
Tensors	1667
Upstream source	https://huggingface.co/nvidia/parakeet-tdt-1.1b
Upstream licence	cc-by-4.0
Licence class	attribution-required
Registry model id	parakeet-tdt-1.1b
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 Parakeet-TDT-1.1B (English ASR — FastConformer encoder + TDT decoder, 1.1B scale-up of the Parakeet-TDT-0.6B-v3 topology). Model weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) NVIDIA. Source: https://huggingface.co/nvidia/parakeet-tdt-1.1b

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 parakeet-tdt-1.1b.gguf
# expect: 5abd74cdffd5795b69b808f3c2164687cb906c181dfe19bf5e76bf3cad82126a