You can deploy this model and start earning money today!

vokra/
hifigan-libritts-22050

Name: hifigan-libritts-22050
Availability: InStock

vokra

gguf

apache-2.0

Views

No views yet

hifigan-libritts-22050 (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
`hifigan-libritts-22050.gguf`	53.2 MB	`4bad4c8e619c8e04852ef23b1bef1756bc94790ba90d0fe031dbbd3df2302273`

Usage

bash

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o hifigan-libritts-22050.gguf \
  https://huggingface.co/vokra/hifigan-libritts-22050/resolve/main/hifigan-libritts-22050.gguf

vokra-cli run --model hifigan-libritts-22050.gguf --input input.wav

Provenance

Field	Value
Architecture	`hifigan_vocoder`
Tensors	234
Upstream source	speechbrain/tts-hifigan-libritts-22050Hz (HiFi-GAN vocoder, LibriTTS 22050Hz, apache-2.0)
Upstream licence	`apache-2.0`
Licence class	`permissive`
Registry model id	`tts-hifigan-libritts-22050hz`
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 hifigan-libritts-22050.gguf
# expect: 4bad4c8e619c8e04852ef23b1bef1756bc94790ba90d0fe031dbbd3df2302273