You can deploy this model and start earning money today!

vokra/
lang-id-voxlingua107

Name: lang-id-voxlingua107
Availability: InStock

vokra

gguf

apache-2.0

Views

No views yet

lang-id-voxlingua107 (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
`lang-id-voxlingua107.gguf`	80.5 MB	`46c320e7250ed2fc3d62c383c7f52b6d0a318a169e3ba5322f2187f7a1e1b8e2`

Usage

bash

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o lang-id-voxlingua107.gguf \
  https://huggingface.co/vokra/lang-id-voxlingua107/resolve/main/lang-id-voxlingua107.gguf

vokra-cli run --model lang-id-voxlingua107.gguf --input input.wav

Provenance

Field	Value
Architecture	`lang_id_ecapa`
Tensors	200
Upstream source	speechbrain/lang-id-voxlingua107-ecapa (ECAPA-TDNN + 107-class lang-id, apache-2.0)
Upstream licence	`apache-2.0`
Licence class	`permissive`
Registry model id	`lang-id-voxlingua107-ecapa`
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 apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

bash

shasum -a 256 lang-id-voxlingua107.gguf
# expect: 46c320e7250ed2fc3d62c383c7f52b6d0a318a169e3ba5322f2187f7a1e1b8e2