Any-to-Any
Transformers
ONNX
Safetensors
English
Chinese
multimodal
audio
video
speech
streaming
full-duplex
long-video
custom-code
Instructions to use inclusionAI/Realtime-Venus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inclusionAI/Realtime-Venus with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("inclusionAI/Realtime-Venus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Having a blast
#1
by chris-hc - opened
I'm having a blast with this model tonight. I quantized the weights to nvfp4 and it seems smart enough, but I can't run full weights on my 16gb 5080.
I did run into an accumulator error, where after so many chunks I would oom because vram reclaim only occurs for new sessions.
Ah! Discovered the sliding window! No need for the memory guard hack.