reazonspeech-nemo-v2 (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
reazonspeech-nemo-v2.gguf	2362.5 MB	0b0349f61cb47f8c01497f14554731bc2a5555152e97d62875f9d0c10b9384ae

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o reazonspeech-nemo-v2.gguf \
  https://huggingface.co/vokra/reazonspeech-nemo-v2/resolve/main/reazonspeech-nemo-v2.gguf

vokra-cli run --model reazonspeech-nemo-v2.gguf --input input.wav

Provenance

Field	Value
Architecture	reazonspeech_nemo_v2
Tensors	965
Upstream source	reazon-research/reazonspeech-nemo-v2 (Longformer local attention Japanese long-form ASR, ReazonSpeech 19,000h Japanese corpus, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	reazonspeech-nemo-v2
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 reazonspeech-nemo-v2.gguf
# expect: 0b0349f61cb47f8c01497f14554731bc2a5555152e97d62875f9d0c10b9384ae