titanet-l (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
titanet-l.gguf	96.9 MB	17388234419f1208a39adc6c19faadcfde918848da663b6f008c8fc3e7f71f85

Usage

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

vokra-cli run --model titanet-l.gguf --input input.wav

Provenance

Field	Value
Architecture	titanet-large
Tensors	108
Upstream source	nvidia/speakerverification_en_titanet_large (TitaNet-Large speaker verification, VoxCeleb + Fisher + Switchboard + LibriSpeech + SRE, 16 kHz mono → 192-d embedding, CC-BY-4.0)
Upstream licence	cc-by-4.0
Licence class	attribution-required
Registry model id	titanet-large
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 TitaNet-Large (speaker verification, depth-wise-separable Conv1D + Squeeze-Excitation, 16 kHz mono → 192-d embedding). Model weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) NVIDIA. Source: https://huggingface.co/nvidia/speakerverification_en_titanet_large

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 titanet-l.gguf
# expect: 17388234419f1208a39adc6c19faadcfde918848da663b6f008c8fc3e7f71f85