ModelScope 的公共 GitHub 足迹

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Enjoy the magic of Diffusion models!

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

ModelScope: bring the notion of Model-as-a-Service to life.

Open-source, accurate and easy-to-use video speech recognition & clipping tool. LLM-based AI clipping integrated.

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

AgentEvolver: Towards Efficient Self-Evolving Agent System

此仓库未提供描述。

🐿️ Sirchmunk: Raw data to self-evolving intelligence, real-time.

SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.

KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech

[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC

AdaSeq: An All-in-One Library for Developing State-of-the-Art Sequence Understanding Models

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

Collect every awesome work about r1!

此仓库未提供描述。

a toolkit on knowledge distillation for large language models

MotionAgent is your AI assistent to convert ideas into motion pictures.

此仓库未提供描述。

DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.

The evaluation benchmark on MCP servers

Twinkle✨: Training workbench to make your model glow.

Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.

此仓库未提供描述。

Ultron: Collective Intelligence System — Shared Memories, Skills, and Harnesses Across Every Agent

A third-party component library based on Gradio. Integrates Ant Design, Ant Design X, Monaco Editor and more advanced components to help you build applications efficiently.

此仓库未提供描述。

An initiative to replicate Sora

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.1, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.5, Qwen3-Omni, Gemma4, ...).

此仓库未提供描述。

A modular and stable agent sandbox runtime environment.

Open Image Curation Tools

Enjoy easier conversations with LLM

Collection of model-centric MCP servers

[ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.

ModelScope's official MCP Server (in active development).

The source code for: https://modelscope.github.io/sirchmunk-web/

此仓库未提供描述。

此仓库未提供描述。

Langchain integration for ModelScope

面向 AI 辅助科研的开放共建仓库 收集和沉淀科研全流程中的 agents、skills、workflows、tools 与最佳实践

The official Python client to connect with ModelScope Hub.

Collection of various Comfy components.

The github website for twinkle-kit

Equip your agents with skills to interact with ModelScope

此仓库未提供描述。