Automatic Speech Recognition
Transformers
Safetensors
English
voxtral
audio
speculative-decoding
neuron
trainium
distillation
Instructions to use jburtoft/Voxtral-Mini-3B-2507-draft-4layer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jburtoft/Voxtral-Mini-3B-2507-draft-4layer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jburtoft/Voxtral-Mini-3B-2507-draft-4layer")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("jburtoft/Voxtral-Mini-3B-2507-draft-4layer") model = AutoModelForMultimodalLM.from_pretrained("jburtoft/Voxtral-Mini-3B-2507-draft-4layer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 11, | |
| "transformers_version": "5.14.1" | |
| } | |