Xenna/cielvox2-asr-0.6b-GGUF overview
CielVox 2 ASR 0.6B GGUF Quantized automatic speech recognition model for CielVox 2. Use with backend cielvox2 asr . Usage bash LD LIBRARY PATH=build/src:build/…
Runs locally from ~960.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| cielvox-asr-0.6b-q8_0.gguf | GGUF | Q8_0 | 960.2 MB | Download |
Model Details
| Model ID | Xenna/cielvox2-asr-0.6b-GGUF |
|---|---|
| Author | Xenna |
| Pipeline | automatic-speech-recognition |
| License | apache-2.0 |
| Base model | — |
| Last modified | 2026-08-22T20:01:31.000Z |
Model README
---
license: apache-2.0
language:
- ar
- cs
- da
- de
- el
- en
- es
- fa
- fi
- fil
- fr
- hi
- hu
- id
- it
- ja
- ko
- mk
- ms
- nl
- pl
- pt
- ro
- ru
- th
- tr
- uk
- vi
- zh
pipeline_tag: automatic-speech-recognition
tags:
- asr
- speech-recognition
- gguf
- stelnettts
- cielvox2-asr
---
CielVox 2 ASR 0.6B GGUF
Quantized automatic speech recognition model for CielVox 2. Use with --backend cielvox2-asr.
Usage
LD_LIBRARY_PATH=build/src:build/ggml/src \
./build/bin/stelnettts \
--backend cielvox2-asr \
-m cielvox-asr-0.6b-q8_0.gguf \
-f input.wav \
--output-file /tmp/transcript \
-l en \
-t $(nproc) \
--i-have-rightsAchieves ~8.3x realtime on AMD Radeon 780M.
Run Xenna/cielvox2-asr-0.6b-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models