Model Details
Full Model IDmistralai/Voxtral-Mini-4B-Realtime-2602
Pipeline / Taskautomatic-speech-recognition
Libraryvllm
Downloads (all-time)2.2M
Likes1.0K
Last Modified3/11/2026
Author / Orgmistralai
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("automatic-speech-recognition", model="mistralai/Voxtral-Mini-4B-Realtime-2602")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
vllmsafetensorsvoxtral_realtimemistral-commonautomatic-speech-recognitionenfresderuzhjaitptnlarhikoarxiv:2602.11298base_model:mistralai/Ministral-3-3B-Base-2512base_model:finetune:mistralai/Ministral-3-3B-Base-2512license:apache-2.0eval-resultsdeploy:sagemakerregion:us
More Speech Recognition Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🎙️ Task: Speech Recognition
This model is designed for the Speech Recognition task. Explore more models for this use case.
All Speech Recognition Models →📊 Popularity
⬇ Downloads2.2M
❤️ Community Likes1.0K
🛠️ Requirements
- →Install: pip install vllm
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.