Owner

OpenMOSS

16 indexed repositories · View on GitHub

• MOSS

  An open-source, tool-augmented conversational language model from Fudan University

  Python · 12251 stars

• MOSS-TTS-Nano

  A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation

  Python · 4382 stars

• MOSS-TTS

  An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

  Python · 4116 stars

• MOSS-Transcribe-Diarize

  A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness

  Python · 2041 stars

• Awesome-WAM

  A curated collection of papers, explainers, and resources on World Action Models for embodied AI

  HTML · 1424 stars

• MOSS-TTSD

  A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning

  Python · 1400 stars

• MOVA

  A foundation model that generates synchronized video and audio in a single model

  Python · 1117 stars

• AnyGPT

  A unified multimodal language model based on discrete sequence modeling

  Python · 882 stars

• MOSS-VL

  An open-weight 11B model series for long-form and real-time video understanding

  HTML · 708 stars

• MOSS-Audio

  An open-source model for understanding speech, environmental sounds, and music through captioning, question answering, and reasoning

  Python · 665 stars

• EasyWAM

  A unified framework for training, fine-tuning, and evaluating World Action Models

  Python · 295 stars

• Llamascopium

  A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods

  Python · 228 stars

• OpenETA

  An embodied task agent that connects perception, action, verification, and learning in a continuous physical-world loop

  Python · 183 stars

• MOSS-Video-Preview

  An 11B model for real-time video understanding with gated cross-attention and streaming inference

  Python · 171 stars

• SWE-bench-Science

  A benchmark for testing whether coding agents can resolve engineering tasks in scientific software

  Python · 80 stars

• FDU-AI-PRML-2024Fall

  Assignments and exercises for the Fall 2024 Pattern Recognition and Machine Learning course at Fudan University

  Python · 6 stars