moss-audio-tokenizer-nano (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
moss-audio-tokenizer-nano.gguf	83.8 MB	440f5f9a96bd6e03aeb5ee04edb333166b01ded5392bbc5b92ae5fe5a1349290

Usage

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

vokra-cli run --model moss-audio-tokenizer-nano.gguf --input input.wav

Provenance

Field	Value
Architecture	moss_audio_tokenizer
Tensors	374
Upstream source	OpenMOSS-Team/MOSS-Audio-Tokenizer (MOSS-Audio-Tokenizer codec Full ~1.77B params F32, arXiv:2602.10934, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	moss-audio-tokenizer
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

shasum -a 256 moss-audio-tokenizer-nano.gguf
# expect: 440f5f9a96bd6e03aeb5ee04edb333166b01ded5392bbc5b92ae5fe5a1349290