ModelScope

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

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

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

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

The evaluation benchmark on MCP servers

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.

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

Mcore Bridge — swift 4.6.0.dev0 documentation

a toolkit on knowledge distillation for large language models

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

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

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

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).

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

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

FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

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