bytedance/SALMONN
ByteDance/Tsinghua research family of multi-modal LLMs processing speech, audio, and video through unified architectures.
Not currently ranked — collecting fresh signals.
star history
SALMONN is a suite of multi-modal large language models developed by ByteDance and Tsinghua University that process and understand audio, speech, video, and text in a unified framework. The project includes multiple specialized variants such as video-SALMONN for audio-visual understanding, ELLSA for streaming full-duplex multimodal perception, and speech quality assessment models. Each branch provides model weights and inference code, with research published at major ML venues including ICLR and ICML.
Frequently asked
- What is bytedance/SALMONN?
- ByteDance/Tsinghua research family of multi-modal LLMs processing speech, audio, and video through unified architectures.
- Is SALMONN open source?
- Yes — bytedance/SALMONN is open source, released under the Apache-2.0 license.
- How popular is SALMONN?
- bytedance/SALMONN has 1.5k stars on GitHub.
- Where can I find SALMONN?
- bytedance/SALMONN is on GitHub at https://github.com/bytedance/SALMONN.