Model Intelligence Sheet
asmanovlev/whisper-small-ru-v2-gguf overview
whisper small ru v2 GGUF FP16 GGUF quantization of artyomboyko/whisper small ru v2 https://huggingface.co/artyomboyko/whisper small ru v2 — a fine tuned Whispe…
Runs locally from ~461.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| whisper-small-ru-fp16.gguf | GGUF | GGUF | 461.1 MB | Download |
Model Details
| Model ID | asmanovlev/whisper-small-ru-v2-gguf |
|---|---|
| Author | asmanovlev |
| Pipeline | automatic-speech-recognition |
| License | apache-2.0 |
| Base model | artyomboyko/whisper-small-ru-v2 |
| Last modified | 2026-06-30T10:22:55.000Z |
Model README
---
language:
- ru
license: apache-2.0
library_name: gguf
pipeline_tag: automatic-speech-recognition
base_model: artyomboyko/whisper-small-ru-v2
tags:
- whisper
- russian
- gguf
- fp16
---
whisper-small-ru-v2 GGUF (FP16)
GGUF quantization of artyomboyko/whisper-small-ru-v2 — a fine-tuned Whisper small model for Russian speech recognition.
Format
- Quantization: FP16 (no quality loss vs original F32)
- Size: 483 MB (50% of original 967 MB)
- Architecture: whisper-small (12 encoder layers, 12 decoder layers, 768 hidden dim)
- Sample rate: 16000 Hz (mono)
Usage with whisper.cpp
git clone https://github.com/ggerganov/whisper.cpp
cd whisper.cpp
wget https://huggingface.co/asmanovlev/whisper-small-ru-v2-gguf/resolve/main/whisper-small-ru-fp16.gguf
make
./main -m whisper-small-ru-fp16.gguf -f audio.wav -l ruPerformance
On Xiaomi 11T (Dimensity 1200, ARMv8.2+ with NEON FP16):
- Real-time transcription with whisper.cpp
- ~2x faster than F32 on Cortex-A78 cores
Credits
- Original model: artyomboyko/whisper-small-ru-v2
- GGUF conversion: whisper.cpp
Run asmanovlev/whisper-small-ru-v2-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models