OpenMOSS

@Open_MOSS

An open research lab building artificial general intelligence. Join Discord ⚡️ discord.gg/Xf3aXddCjc

Joined January 2025

35 Following

915 Followers

Replies Reposts Media

Pinned
OpenMOSS
@Open_MOSS
Oct 17
Welcome to try our new models!
MOSS
@MOSS_Global
Oct 16
🤗 MOSS-Image is now open source on @huggingface . Built on a 5B Diffusion Transformer (DiT), MOSS-Image brings Chinese & English text rendering and controllable layouts to image generation — from posters and infographics to creative visuals.@Open_MOSS What it offers: 📝 Long
OpenMOSS
@Open_MOSS
Jul 16
🔥 MOSS-Transcribe-Diarize is among the top trending models on @huggingface . A few weeks after release, the model has been explored by developers and researchers worldwide.@MosiAI_Official Built with an end-to-end audio-to-structured-transcript paradigm: • 0.9B open-source
3
OpenMOSS
@Open_MOSS
Jul 16
🥇 MOSS-Transcribe-Diarize ranked #1 in the 2nd MLC-SLM Challenge at INTERSPEECH 2026 @MosiAI_Official The challenge spans 14 languages: English, French, German, Italian, Portuguese, Spanish, Japanese, Korean, Russian, Thai, Vietnamese, Tagalog, Urdu, and Turkish.
2
OpenMOSS
@Open_MOSS
Jul 14
🤗 MOSS-VL-Realtime is now open source on @huggingface . The 11B model family supports text, single and multiple images, single and multiple videos, and interleaved visual-text inputs in Chinese and English.@MosiAI_Official Highlights: 🏗️ Cross-Attention architecture
MOSS
00:00
MOSS
2
OpenMOSS
@Open_MOSS
Jul 9
@MosiAI_Official we're open-sourcing MOSS-Transcribe-Diarize-0.9B on @huggingface 🚀 An end-to-end ASR model for long, multi-speaker audio: transcription + speaker labels + timestamps in one generation pass. Thank you @sgl_project @vllm_project @Prince_Canuma @lllucas for
MOSS
00:00
MOSS
MOSS
@MOSS_Global
Jul 9
01:17
🤗 MOSS-Transcribe-Diarize-0.9B is now open source on @huggingface. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one
4