Downloads · 30 days
35
7% of all-time downloads
ICTNLP/stream-omni-8b
stream-omni-8b is a any-to-any model from ICTNLP. Use it for the any-to-any task on the model card, and read the license before you ship it in a product. The card lists the license as gpl-3.0.
[](https://arxiv.org/abs/2506.13642) [](https://github.com/ictnlp/Stream-Omni) [](https://huggingface.co/ICTNLP/stream-omni-8b)
Downloads · 30 days
35
7% of all-time downloads
All-time downloads
489
Public
Parameters
12.7B
25.5 GB on disk
Likes
50
Public
Click a slice to open those files.
.safetensors25.5 GB · 100%
From the Hugging Face model README
Shaolei Zhang, Shoutao Guo, Qingkai Fang, Yan Zhou, Yang Feng*
The introduction and usage of Stream-Omni refer to https://github.com/ictnlp/Stream-Omni.
Stream-Omni is an end-to-end language-vision-speech chatbot that simultaneously supports interaction across various modality combinations, with the following features💡:
| Microphone Input | File Input |
|---|---|
| <video src='https://github.com/user-attachments/assets/99325a91-b81c-4fd1-a68e-c0628d5784fe' width="100%"/> | <video src='https://github.com/user-attachments/assets/bcb37b15-6c8c-4eae-845e-5da10aaac11e' width="100%"/> |
[!NOTE]
Stream-Omni can produce intermediate textual results (ASR transcription and text response) during speech interaction, offering users a seamless "see-while-hear" experience.