yue-upsampler (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
yue-upsampler.gguf	69.2 MB	17df9c667c931544cf84545266d07e3598a9528d751ca6f281fffd305f4409ff

Usage

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

vokra-cli run --model yue-upsampler.gguf --input input.wav

Provenance

Field	Value
Architecture	yue_upsampler
Tensors	81
Upstream source	m-a-p/YuE-upsampler (YuE Vocos vocoder head, VocosBackbone 8-layer + ISTFTHead n_fft=3528 hop=882 @ 44.1 kHz, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	yue-upsampler
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 yue-upsampler.gguf
# expect: 17df9c667c931544cf84545266d07e3598a9528d751ca6f281fffd305f4409ff