mossformer2-ss-16k (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
mossformer2-ss-16k.gguf	212.7 MB	822516b75873dbeb814dac72f7ca0b5fb75254dd051dfdfdda54987347330f0c

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o mossformer2-ss-16k.gguf \
  https://huggingface.co/vokra/mossformer2-ss-16k/resolve/main/mossformer2-ss-16k.gguf

vokra-cli run --model mossformer2-ss-16k.gguf --input input.wav

Provenance

Field	Value
Architecture	mossformer2_ss_16k
Tensors	1076
Upstream source	alibabasglab/MossFormer2_SS_16K (Alibaba SGLab cocktail-party / multi-speaker speech separator at 16 kHz, FSMN + gated-attention topology, ClearerVoice-Studio project, Zhao et al. 2024 Interspeech, Apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	mossformer2_ss_16k
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 mossformer2-ss-16k.gguf
# expect: 822516b75873dbeb814dac72f7ca0b5fb75254dd051dfdfdda54987347330f0c