JIA-Lab-research / MGM-Omni
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
Why this job: matched by what the repo talks about: speech, llm, scal, personaliz
What it does
We present MGM-Omni, an omni-chatbot capable of processing text, image, video, and speech inputs, and can generate both text and speech responses. Based on MiniGemini and MiniGemini v2 (Lyra), MiniGemini-Omni (MGM-Omni) enables long-form speech understanding and generation, as well as voice cloning in both Chinese and English.
Get started
git clone https://github.com/dvlab-research/MGM-Omni.git - Maintenance
- Active
- Last commit 4 months ago
- Stars
- 202
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 55% closed
- 5 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| OpenMOSS / MOSS-TTS-Nano | 4,665 | 2 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- audio-language-model
- multi-modal-large-language-model
- multi-modality
- multimodal
- text-to-speech
Project record
- JobSpeech and audio
- StatusListed
- Commits34
- Forks11
- Watching7
- Stars in 28 days0
- CreatedAug 17, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026