You can deploy this model and start earning money today!

vokra/
clap-htsat-fused

Name: clap-htsat-fused
Availability: InStock

vokra

gguf

apache-2.0

Views

No views yet

clap-htsat-fused (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
`clap.gguf`	585.6 MB	`96e8084d73f2d7f14ce6ff94b7d93d0c9c9b3d9b1b381e39fec0de617f6b6f0b`

Usage

bash

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

vokra-cli run --model clap.gguf --input input.wav

Provenance

Field	Value
Architecture	`clap`
Tensors	458
Upstream source	laion/clap-htsat-fused (contrastive language-audio pretraining, HTSAT audio encoder + text encoder, apache-2.0)
Upstream licence	`apache-2.0`
Licence class	`permissive`
Registry model id	`clap-htsat-fused`
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 clap.gguf
# expect: 96e8084d73f2d7f14ce6ff94b7d93d0c9c9b3d9b1b381e39fec0de617f6b6f0b