AI & ML interests
LLM
Recent Activity
Papers
MOSS-Image Technical Report
Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position
Articles
MOSS-Speech Demo
True Speech-to-Speech Language Model
README
OpenMOSS Team of SII
MOSS-Image Workflow
MOSS-Image text-to-image as a gr.Workflow node canvas.
MOSS-VL-Realtime
Live streaming video chat ā ask while the model watches
MOSS-VL-Instruct-0708
Image and video understanding with MOSS-VL multimodal model
MOSS-Music-8B-Instruct
Analyze uploaded music and get detailed textual insights
MOSS-VL-Realtime
Realtime VLM for image and video understanding
MOSS Audio Tokenizer Series
Reconstruct audio with customizable tokenization layers
MOSS-SoundEffect v2.0 Demo
Official Gradio demo for MOSS-SoundEffect-v2.0.
MOSS TTS V1.5
Generate speech from text with optional voice cloning
MOSS TTS Nano
ZeroGPU Nano-TTS voice clone demo
MOSS TTS Realtime
A simple gradio for demonstrating MOSS-TTS-Realtime
MOSS Audio 8B Thinking
Generate answers from uploaded audio or video
MOSS-VL
MOSS-VL: Toward Advanced Video Understanding
MOSS Transcribe Diarize
Transcribe audio or video with speaker diarization
MOSS TTSD
MOSS-TTSD: Text to Spoken Dialogue Generation
MOSS VoiceGenerator
A gradio platform for demonstrating MOSS-VoiceGenerator
MOSS TTS
A simple gradio platform for demonstrating MOSS-TTS capabili