Downloads · 30 days
381
14% of all-time downloads
Voxtral-Mini-4B-Realtime-2602-fp16
mlx-community/Voxtral-Mini-4B-Realtime-2602-fp16
Voxtral-Mini-4B-Realtime-2602-fp16 is a automatic speech recognition model from mlx-community. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
This is a float16 MLX conversion of mistralai/Voxtral-Mini-4B-Realtime-2602, Mistral AI's streaming speech-to-text model.
All-time downloads
2.7K
Public
Parameters
4.4B
8.9 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors8.9 GB · 100%
Parameter types
How the weights are stored.
F164.4B · 100%
Base models
Model card
From the Hugging Face model README
Voxtral Mini 4B Realtime — MLX fp16
This is a float16 MLX conversion of mistralai/Voxtral-Mini-4B-Realtime-2602, Mistral AI's streaming speech-to-text model.
Runs via mlx-audio.
Key Details
| Parameters | 4B (~3.4B LM + ~0.6B Audio Encoder) |
| Precision | float16 (full precision) |
| Base model | mistralai/Voxtral-Mini-4B-Realtime-2602 |
| Languages | 13 (Arabic, German, English, Spanish, French, Hindi, Italian, Dutch, Portuguese, Chinese, Japanese, Korean, Russian) |
| License | Apache 2.0 |
See also: int4 variant (smaller, faster)
Usage
pip install mlx-audio[stt]
from mlx_audio.stt.utils import load
model = load("mlx-community/Voxtral-Mini-4B-Realtime-2602-fp16")
# Transcribe audio
result = model.generate("audio.wav")
print(result.text)
# Streaming transcription
for chunk in model.generate("audio.wav", stream=True):
print(chunk, end="", flush=True)
# Adjust transcription delay (lower = faster but less accurate)
result = model.generate("audio.wav", transcription_delay_ms=480)
Recommended Settings
| Setting | Value | Notes |
|---|---|---|
| Temperature | 0.0 | Always use greedy decoding |
| Transcription delay | 480ms | Sweet spot of accuracy vs. latency |
| Delay range | 80ms – 2400ms | Multiples of 80ms |
Benchmarks (from upstream)
FLEURS (13 languages, WER%)
| Delay | AVG | EN | FR | DE | ES | ZH | JA | KO |
|---|---|---|---|---|---|---|---|---|
| 160ms | 12.60 | 6.46 | 9.75 | 9.50 | 5.34 | 17.67 | 19.17 | 19.81 |
| 480ms | 8.72 | 4.90 | 6.42 | 6.19 | 3.31 | 10.45 | 9.59 | 15.74 |
| 960ms | 7.70 | 4.34 | 5.68 | 4.87 | 2.98 | 8.99 | 6.80 | 14.90 |
| 2400ms | 6.73 | 4.05 | 5.23 | 4.15 | 2.71 | 8.48 | 5.50 | 14.30 |
Long-form English (WER%)
| Delay | Meanwhile | Earnings-21 | Earnings-22 | TEDLIUM |
|---|---|---|---|---|
| 480ms | 5.05 | 10.23 | 12.30 | 3.17 |
Architecture
- Causal audio encoder (~0.6B) with sliding window attention — enables true streaming
- Language model decoder (~3.4B) based on Ministral-3B with adaptive RMS norm conditioned on transcription delay
- 4x downsampling from encoder to decoder (frame rate = 12.5 Hz)
- Both components use sliding window attention for unbounded audio length
More Info
- Task
- Automatic Speech Recognition
- Library
- mlx
- Type
- voxtral_realtime
- License
- apache-2.0
- Languages
- ar, de, en, es, fr, hi
- Created
- Feb 6, 2026
- Updated
- Feb 9, 2026