Downloads · 30 days
9
26% of all-time downloads
vokra/nisqa-v2-weight
nisqa-v2-weight is a machine learning model from vokra. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for vokra. The card lists the license as cc-by-nc-sa-4.0.
Converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.
Downloads · 30 days
9
26% of all-time downloads
All-time downloads
34
Public
Repo size
1 MB
Likes
0
Public
Click a slice to open those files.
.gguf1 MB · 97%
From the Hugging Face model README
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.
| File | Size | SHA-256 |
|---|---|---|
nisqa-v2-weight.gguf | 1.0 MB | a2cacbe6f81ea2e8255eb0e2137d70d245823758e1cc4bb180c6b7cccc131e07 |
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o nisqa-v2-weight.gguf \
https://huggingface.co/vokra/nisqa-v2-weight/resolve/main/nisqa-v2-weight.gguf
vokra-cli run --model nisqa-v2-weight.gguf --input input.wav
| Field | Value |
|---|---|
| Architecture | nisqa_v2_weight |
| Tensors | 94 |
| Upstream source | github.com/gabrielmittag/NISQA (non-intrusive speech quality assessment CNN + self-attention, Mittag et al. 2021 arXiv:2104.09494, CC-BY-NC-SA-4.0 — owner §3.1 sign-off required, publish requires --allow-noncommercial + SA cascade obligation) |
| Upstream licence | cc-by-nc-sa-4.0 |
| Licence class | non-commercial-share-alike |
| Registry model id | nisqa_v2_weight |
| 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.
The weights are distributed under cc-by-nc-sa-4.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.
This weight is cc-by-nc-sa-4.0, and that licence is not discharged by attribution alone. It attaches to derivatives.
The upstream weight is cc-by-nc-sa-4.0. It is republished here so the model can be evaluated and used for research, and the licence is unchanged by conversion.
shasum -a 256 nisqa-v2-weight.gguf
# expect: a2cacbe6f81ea2e8255eb0e2137d70d245823758e1cc4bb180c6b7cccc131e07