qwen3-asr-1.7b (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
qwen3-asr-1.7b.gguf	4480.8 MB	5e999dafdc061abfe603678048054dc4117b6366389691bb459725037eaf55e6

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o qwen3-asr-1.7b.gguf \
  https://huggingface.co/vokra/qwen3-asr-1.7b/resolve/main/qwen3-asr-1.7b.gguf

vokra-cli run --model qwen3-asr-1.7b.gguf --input input.wav

Provenance

Field	Value
Architecture	qwen3_asr
Tensors	708
Upstream source	Qwen/Qwen3-ASR-1.7B (Qwen3-flavour multilingual ASR: audio encoder + Qwen3 LM decoder, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	qwen3-asr-1.7b
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 qwen3-asr-1.7b.gguf
# expect: 5e999dafdc061abfe603678048054dc4117b6366389691bb459725037eaf55e6