moss-voice-generator (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-voice-generator.restamped.gguf	4032.4 MB	a7b499dde92c70534b2cfb6178e5ffb513aa490ee1fe58c0bda2a76418ec2eda

Usage

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

vokra-cli run --model moss-voice-generator.restamped.gguf --input input.wav

Provenance

Field	Value
Architecture	moss_tts
Tensors	343
Upstream source	OpenMOSS-Team/MOSS-VoiceGenerator
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	moss-voice-generator
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.

Attribution required

OpenMOSS Team (Fudan) — MOSS-VoiceGenerator (moss_tts_delay variant)

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 moss-voice-generator.restamped.gguf
# expect: a7b499dde92c70534b2cfb6178e5ffb513aa490ee1fe58c0bda2a76418ec2eda