Automatic Speech Recognition
Transformers
Safetensors
voxtral_realtime
fp8
quantized
vllm
mistral
compressed-tensors
llm-compressor
Instructions to use ghecko78/Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ghecko78/Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ghecko78/Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ghecko78/Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic") model = AutoModelForMultimodalLM.from_pretrained("ghecko78/Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 29590b1e1d57c4cb967af1c142ab918ade06d778ac75327278cc890738704dbc
- Size of remote file:
- 5.83 GB
- SHA256:
- 5afe289389dbd530fbc595280b27731fd7351e6f1665d89c060f98f79281a51d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.